Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: Computer Science. The day in computer science: software, systems and theory on arXiv.
Tom: I'm Tom.
Jane: And I'm Jane, here with Lu, Meng and our in-house large language model, Lalam.
Tom: We're looking at the paper: "Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation".
Jane: Here's the gist of the paper. Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs The proposed fairness-aware retrieval framework models and controls this bias Experimental results show that our method effectively mitigates generation bias while preserving relevance.
Tom: The authors propose a three-stage framework for fairness-aware retrieval optimization in RAG systems This approach integrates controlled bias injection, bias propagation modeling, and optimization-based retrieval.
Jane: The key novelty of our approach lies in extending bias control from top1 retrieval to position-aware top-k retrieval This involves modeling how bias propagates across multiple retrieved documents and leveraging this model to guide fairness-aware retrieval optimization.
Tom: Modeling Bias Propagation The second stage aims to detect how bias in retrieved documents propagates to the final generated outputs This is achieved by fitting a linear regression model that relates position-wise embedding bias to the final system bias.
Title and authors: Tom: So we're looking at this paper called "Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation". It tackles a big problem in AI systems: when you use retrieval augmented generation, or RAG, the way documents are pulled out of a knowledge base can actually introduce bias that then gets baked into what the model generates.
Jane: That sounds like it’s addressing something we see happening all the time where simple search methods can end up skewing an AI's answer in ways we don't want. What exactly is this paper trying to do with that problem?
Lu: Basically, they propose a three-stage framework to model and control that bias. It starts by injecting controlled bias into the retrieval process, then modeling how that bias moves through the different document positions, and finally using an optimization method to balance getting relevant answers with keeping those biases in check.
Meng: Modeling propagation sounds heavy. I always worry about what happens when you try to control something in a massive system like this—how do you actually know if your fix is working without just adding more complexity?
Lalam: The core idea here is that the bias isn't just in the documents themselves, but in *how* those documents are ordered and presented to the final language model. They model how bias at different retrieval positions influences the final output, which helps them understand why selection matters so much.
Tom: So it moves beyond just looking at one document or one search result. It looks at the entire sequence of retrieved documents and how their placement together affects the system's overall behavior, which is a key difference here.
Jane: And then they have this optimization strategy involving something called Quadratic Fairness via Dual Hyperplane Approximation, or FARO, to handle that trade-off between getting a good answer and ensuring it's fair. How does that help us actually find the right balance?
Lu: The FARO framework is what makes the optimization efficient. It takes a really complicated fairness problem that's globally coupled—meaning every choice affects every other choice—and breaks it down into many smaller, independent subproblems for each question.
Meng: Decomposing a global problem into smaller ones is good for computation, but I’m concerned about what happens when we do that decomposition; does it lose the overall picture of fairness?
Tom: The paper claims this decomposition preserves the ability to explore trade-offs between relevance and fairness. They show that you can still find solutions along that frontier even with these smaller subproblems.
Jane: So, if I'm just trying to get a fast, relevant answer right now, does this framework slow me down too much for everyday use?
Lalam: The experimental results show they effectively reduce generation bias while maintaining competitive relevance performance. They found that the linear model they fit to the data provides a good approximation of how those position-wise biases combine to create the final system bias.
Title and authors: Tom: That's what I like to see—a tractable way to approximate something that is inherently complex, which is exactly what we need when we are shipping models at scale.
Lu: The paper shows that this combination of a position-aware model and a scalable optimization framework allows for effective and practical fairness-aware retrieval in RAG systems. It's not just theoretical math; it has been tested on multiple datasets, looking at political and gender bias settings.
Meng: I need to know about the real-world deployment cost. If we use this FARO method, how much extra computation are we adding compared to a standard top-k retrieval setup?
Tom: The paper suggests that FARO provides significant improvements in scalability and flexibility compared to linear programming, especially as the number of retrieved documents, k, gets larger. LP has to recompute the solution from scratch every time the fairness constraint changes.
Jane: So for a user who just wants a quick search result today, does this mean we can still get fast performance?
Lu: They found that FARO offers flexibility in navigating that relevance and fairness trade-off by letting you generate multiple candidate solutions along the fairness relevance frontier. It’s useful when the requirements change dynamically, which is common in real-world applications.
Lalam: The authors also admit some limitations, though. They point out that their bias propagation model relies on linearity and independence assumptions, and it focuses specifically on binary group fairness rather than multi-group fairness definitions.
Meng: That's a standard caveat I expect. What about the underlying language model? If the base model itself is already heavily biased, does this framework fix everything?
Tom: The paper states that the effectiveness of bias mitigation depends on the intrinsic biases of the underlying language models. So, it’s a system-level control, not a total fix for every possible input source.
Jane: So to wrap up this discussion on "Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation," we see a principled approach that combines controlled bias injection, position modeling, and the efficient FARO optimization to manage bias propagation in top-k RAG settings.
Lu: It provides a flexible and efficient alternative by decomposing the global problem into independent subproblems and generating multiple candidate solutions along the fairness relevance frontier. This is much more practical than traditional linear programming when we need dynamic controls.
Meng: For production, this sounds like a promising way to introduce fairness constraints without completely crippling our retrieval speed, provided the computational overhead from the FARO decomposition doesn't become too high at scale.
Lalam: The main implication for me is that it gives us a concrete mechanism to link retrieval decisions directly to generation outcomes, which is crucial for building trust in these RAG systems.
Tom: Yeah, so combining a position-aware bias model with this scalable optimization framework seems like the path forward for practical fairness awareness in RAG. It’s a solid step toward making sure the information we feed the language model is as unbiased as possible.
The paper's summary: Tom: So, we just finished looking at the technical details of this paper on fairness-aware retrieval optimization for RAG systems, and now we need to talk about what all that means in plain English for us listening right now.
Jane: Right, so essentially, they’ve built a system that doesn't just pull documents randomly or based on keywords; it actively tries to make sure the search results are fair before the final AI answer is even generated. It models how bias creeps in at every single step of finding information and then uses this optimization framework to balance getting a good, relevant answer with keeping those biases from skewing the output.
Lu: What’s really interesting about their approach is that they aren't just looking at fairness for one search query; they are modeling how bias propagates across the whole set of documents retrieved. They fit a linear model to show exactly how the bias in document position influences the final output of the language model, which gives them a concrete way to see where things go wrong.
Meng: But I always worry about complexity when we're shipping things. How do you actually make this work efficiently? Is this just going to turn retrieval into something that takes forever on real traffic?
Tom: The optimization part is what makes it scalable. They use something called the Quadratic Fairness via Dual Hyperplane Approximation, or FARO. It’s clever because it takes one huge, complicated fairness problem—which is globally coupled, meaning every choice affects every other choice—and breaks it down into many smaller subproblems for each question individually.
Jane: So if we think about it practically, this means that instead of running one massive calculation to find the perfect fair search result for a whole database, you run several smaller calculations. It’s like solving a big puzzle by solving many small pieces at once.
Lu: Exactly. And they show that this decomposition actually lets you explore the trade-off between relevance—getting the right answer—and fairness in a flexible way. You can generate different candidate solutions along that line, so you can pick what feels right for your specific use case without having to re-solve the whole system every time you change a rule.
Tom: The experimental results they showed are pretty strong. They proved that this method effectively cuts down on generation bias while still keeping the relevance performance competitive with standard top-k retrieval methods. That’s a tangible win for production engineers because it means we get better quality without necessarily tanking our speed metrics.
Jane: And they did mention some limitations, which is important because you can't just take any paper at face value. They admitted that their bias propagation model assumes things are linear and independent, and they focused mainly on binary group fairness, not more complex fairness definitions for multiple groups.
Meng: That makes sense. I wouldn't expect a system to perfectly solve every single social problem out of the box. But if this gives us a tool to guide our current retrieval setup toward better balance with measurable results, that’s valuable for deployment.
Tom: It really is. This paper moves the conversation from just saying "RAG can be biased" to giving us a specific, mathematically grounded method—a position-aware model combined with FARO—that allows us to actively control that bias during the retrieval phase itself.
Jane: And that leads right into the next part of this discussion: what does this actually mean for how we design and trust these systems when they’re used in the real world?
The paper's improvements: Tom: We’ve talked about how they model and optimize bias in retrieval, and now we need to talk about what improvements they actually propose for making this framework even better than it is right now.
Jane: So, the main idea is that the system can be made more precise in two big ways: first, controlling the injection of bias before retrieval even happens by using a probabilistic reranker based on specific groups.
Lu: That means instead of just searching generally, the system can partition its knowledge base into different subsets for different groups and then use a reranker to order documents for each question specifically tailored to those groups.
Meng: Wait, so we can control which documents get chosen based on group membership? How much extra computation is that adding there?
Tom: The benefit is precise manipulation of the embedding bias without having to change the core retriever model itself, and it’s achieved by partitioning the knowledge base and using a reranker.
Jane: Then there’s this position-aware modeling. They suggest fitting a linear regression model to data generated from slight changes in document positions to understand exactly how bias at different spots affects the final AI output.
Lu: That modeling step is key because it provides an interpretable approximation of how all those retrieved documents jointly influence the final answer, which helps us see if our control mechanism is actually working as intended.
Tom: And finally, they really push for using that FARO optimization framework to balance relevance and fairness by letting you explore different trade-offs through a set of surrogate parameters called mu.
Jane: That means you can generate multiple candidate solutions along the line between getting a relevant answer and being fair, allowing practitioners to choose the best balance for their specific needs.
Meng: If I’m shipping this to production, I need that flexibility—being able to explore those trade-offs without needing a complete overhaul of the system every time we get new fairness requirements.
Lu: The implication is that you get a more dynamic and flexible system where you can tune the fairness constraints against performance metrics, which is much better than a fixed setting.
Tom: So, instead of just finding one perfect setup, this framework allows for a set of viable options on that frontier based on how much you prioritize one thing over the other.
Jane: It’s about giving the user control over the trade-off, which is something we see a lot in recommendation systems and search where relevance and ethical considerations often clash.
Lu: The future work they mention is extending this to richer fairness notions than just binary group fairness, so it could potentially handle more nuanced social biases down the line.
Conclusion: Tom: So we’re wrapping up this look at "Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation." To sum it up, this paper gives us a concrete, scalable framework—FARO—to manage the bias that creeps into AI answers during retrieval by modeling how bias moves across document positions and using an efficient optimization strategy.
Jane: What this means for us is that we can move beyond just hoping our retrieval system is fair and start actively engineering it with measurable control over the relevance-fairness trade-off. It shifts fairness from a vague goal to a solvable mathematical problem with defined parameters.
Lu: I think the real impact is showing how you can decompose those big, complicated global problems into smaller, independent subproblems for each question, which makes the optimization computationally feasible at scale where linear programming just breaks down.
Meng: I still have to ask about deployment cost though. If we use this FARO approach, what’s the practical overhead compared to just running a standard top-k search pipeline on our actual traffic?
Tom: The paper suggests that FARO offers better scalability and flexibility than linear programming, especially as you increase the number of retrieved documents, k. It allows for flexible exploration of those trade-offs without having to recompute the whole system from scratch every time you change a fairness requirement.
Jane: It’s a win because it gives us tools that work dynamically, which is essential when question distributions or fairness rules might change based on who’s asking the questions.
Lu: And while they acknowledge their model relies on linearity and independence assumptions, they point out that this framework provides a solid starting point for controlling position-based bias in RAG systems.
Meng: I just want to see if those assumptions hold up when we put it on real traffic. It’s a great theoretical tool, but the robustness under messy, real-world data is what matters most for me right now.
Tom: The authors are clear that the effectiveness of bias mitigation ultimately depends on the intrinsic biases baked into the underlying language models themselves, so this is a system-level control over retrieval.
Jane: So it’s not a magic fix for every single model, but it’s a very powerful tool for engineers to build better guardrails around their RAG pipelines.
Lu: I think the long-term potential lies in extending this beyond binary group fairness to handle more complex social definitions of fairness, which is where the next big research direction should go.
Meng: For now, it’s a solid addition to our toolkit for making sure the information we feed the AI isn't introducing unfairness into its final output.
Tom: That’s what we have today with "Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation." It shows us exactly how to use position awareness and decomposition to gain control over bias in RAG systems.
Jane: It’s a concrete step toward building more trustworthy AI applications where we can actually measure and manage the fairness of what the model finds.
Lu: Next week, we'll be looking at some work on how large language models actually learn and represent that knowledge, which is the foundation for all this retrieval stuff.
Data Science Research Centre, Tampere University · Harokopio University of Athens
cs.DB, cs.IR
Submitted: 2026-05-15
Updated: 2026-11-10
License: http://creativecommons.org/licenses/by/4.0/
Importance score: 78/100
The gist: Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge…
Key concepts
- Controlled Bias Injection via Reranking
- This technique allows users to intentionally manipulate document bias without changing the main search engine. The system divides knowledge into specific groups and uses a probabilistic reranker to select and order documents for each query, enabling precise control over which biased documents are retrieved.
- Position-Aware Bias Propagation Modeling
- This stage models how bias present in the position of a document in the retrieval list affects the final generated answer. It fits a linear regression model to data derived from controlled changes in position-wise embedding bias, showing exactly how multiple retrieved documents jointly influence system bias.
- Quadratic Fairness via Dual Hyperplane Approximation (FARO)
- FARO is an optimization strategy that converts a complex fairness problem into simpler, independent subproblems. It allows the system to efficiently explore the trade-off between relevance and fairness by decomposing the global optimization into manageable per-question tasks.
- Relevance–Fairness Trade-off Exploration
- The FARO framework enables practitioners to flexibly explore different solutions along the line where they balance accuracy (relevance) against fairness. By using surrogate parameters, users can choose settings that prioritize either relevance or fairness based on their specific needs.
Terminology
Summary
Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs The proposed fairness-aware retrieval framework models and controls this bias Experimental results show that our method effectively mitigates generation bias while preserving relevance. p. 0 Fairness-Aware Retrieval Optimization for
Retrieval-Augmented Generation
Yingqi Zhaoa
, Vasilis Efthymioub
, Jyrki Nummenmaaa
, Kostas Stefanidisa
aData Science Research Centre, Tampere University, Tampere, Finland
bHarokopio University of Athens, Athens, Greece
Abstract
Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs. This issue is
particularly challenging in top-k settings, where multiple documents jointly
influence generation.Where the paper says it
Introduction to the Framework
The authors propose a three-stage framework for fairness-aware retrieval optimization in RAG systems This approach integrates controlled bias injection, bias propagation modeling, and optimization-based retrieval. The key novelty of our approach lies in extending bias control from top1 retrieval to position-aware top-k retrieval This involves modeling how bias propagates across multiple retrieved documents and leveraging this model to guide fairness-aware retrieval optimization. p. 6 The framework integrates controlled bias injection,
bias propagation modeling, and optimization-based retrieval, enabling both
the analysis and mitigation of bias in top-k RAG settings. The key novelty of our approach lies in extending bias control from top1 retrieval to position-aware top-k retrieval, modeling how bias propagates
across multiple retrieved documents, and leveraging this model to guide
fairness-aware retrieval optimization.Where the paper says it
Modeling Bias Propagation
The second stage aims to detect how bias in retrieved documents propagates to the final generated outputs This is achieved by fitting a linear regression model that relates position-wise embedding bias to the final system bias. The resulting formulation reveals that system-level bias can be approximated as a weighted combination of position-wise embedding biases. p. 8 This model captures
how bias at different positions contributes to the generated output and provides an interpretable representation of bias propagation. The resulting formulation reveals that system-level bias can be approximated as a weighted
combination of position-wise embedding biases. The learned coefficients reflect the sensitivity of the language model to bias signals at different positions,
and can be interpreted as position-dependent attention weights. This modeling step is critical: it provides a tractable and interpretable
approximation of how multiple retrieved documents jointly influence the final
output, and serves as the foundation for the optimization stage.Where the paper says it
Where the paper says it
Optimization Strategy
The third stage formulates fairness-aware retrieval as an optimization problem and proposes an efficient solution based on Quadratic Fairness via Dual Hyperplane Approximation (FARO) The FARO framework transforms a globally coupled fairness optimization problem into a set of independent subproblems, enabling efficient computation while preserving the ability to explore trade-offs between relevance and fairness. This approach decomposes the global problem into independent per-question subproblems, allowing for flexible exploration of the relevance–fairness trade-off. p. 2 Building on this formulation, we further introduce a scalable optimization
framework based on Quadratic Fairness via Dual Hyperplane Approximation
(FARO). This approach transforms a globally coupled fairness optimization
problem into a set of independent subproblems, enabling efficient computation while preserving the ability to explore trade-offs between relevance and
fairness.Where the paper says it
Experimental Validation
The experimental results demonstrate that our method effectively reduces generation bias while maintaining competitive relevance performance The linear model provides a good fit to the empirical data, supporting its suitability as an approximation of bias propagation in top-k RAG systems. The FARO framework offers flexibility in navigating the relevance–fairness trade-off Overall, the results demonstrate that combining a position-aware bias model with a scalable optimization framework enables effective and practical fairnessaware retrieval in RAG systems. p. 2 Furthermore, the proposed optimization
framework offers flexibility in navigating the relevance–fairness trade-off. Overall, we propose an end-to-end three-stage framework for fairnessaware retrieval optimization in RAG systems.Where the paper says it
Conclusion on Performance
The proposed FARO method offers a flexible and efficient alternative by decomposing the global problem into independent subproblems and generating multiple candidate solutions along the fairness–relevance frontier The results show that FARO provides significant improvements in scalability and flexibility compared to linear programming, especially as k increases. In contrast, LP must recompute the solution from scratch when the fairness constraint changes. p. 4 In contrast, our work explicitly models position-dependent bias
propagation and leverages it for bias mitigation. It is worth noting that there are other works on fairness-aware ranking
in RAG, such as [15], focusing on the fair presentation of retrieved relevant items, thereby enabling the generator to reference its sources in a balanced manner; [16] instead examines whether question associated with certain groups within a specific fairness category systematically achieve higher
accuracy, and studies the roles of exposure, utility, and attribution bias. The framework
supports different levels of fairness constraints and can adapt to varying
application requirements, producing retrieval strategies that maintain high
relevance while mitigating bias. Summary: We introduce an end-to-end framework for fairness-aware
retrieval optimization in top-k RAG systems.Where the paper says it
Where the paper says it
Limitations
Several limitations remain, including the reliance of the proposed bias propagation model on linearity and independence assumptions The formulation focuses on binary group fairness and does not directly extend to multi-group fairness definitions Furthermore, the effectiveness of bias mitigation depends on the intrinsic biases of the underlying language models. Future work includes extending the framework to richer fairness notions and exploring adaptive retrieval strategies that account for question-specific fairness requirements. p. 9 To solve this problem efficiently, we design an optimization framework
that enables flexible trade-offs between these objectives. The framework
supports different levels of fairness constraints and can adapt to varying
application requirements, producing retrieval strategies that maintain high
relevance while mitigating bias.Where the paper says it
References
[1] Vaswani et al., Attention is All you Need, in: Advances in Neural Information Processing Systems, volume 30, Curran Associates, Inc. p. 0 Keywords: Retrieval-Augmented Generation (RAG), Fairness-Aware
Retrieval, Bias Propagation, Fair Ranking. Introduction
Recent advances in Large Language Models (LLMs) have significantly improved the ability of artificial intelligence systems to generate coherent and
contextually relevant text [1, 2]. The remainder of the paper is structured around the proposed fairnessaware retrieval pipeline. Section 2 reviews related work on bias in RAG systems and fairness-aware ranking.Where the paper says it
Where the paper says it
[2] J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A Radford, J Wu et al., Scaling Laws for Neural Language Models
[3] Z.-Jie Ji et al., Survey of hallucination in natural language generation
[4] P. Lewis, E. Perez, A. Piktus, F. Petroni, V Karpukhin et al., Retrieval-augmented generation for knowledge-intensive nlp tasks
[5] M Hu et al., No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vi36ilant Users
[6] X Wu et al., Does RAG Introduce Unfairness in LLMs? p. 3 Related Work
2. Bias Introduction and Mitigation in RAG
Although Retrieval-Augmented Generation (RAG) has been widely adopted
to improve the performance of Large Language Models (LLMs) and reduce
hallucinations, recent studies have shown that it may also introduce or amplify bias in generated outputs.Where the paper says it
[7] R Ranjan, S Gupta, S N Singh, A comprehensive survey of bias in llms: Current landscape and future directions
[8] E Pitoura et al., Fairness in rankings and recommendations: an overview
[9] G et al., Bias and Fairness in Large Language Models: A Survey
[10] A Singh, T Joachims, Fairness of Exposure in Rankings
[11] T Kim et al., Mitigating Bias in RAG: Controlling the Embedder
[12] Y Zhao et al., ReFaRAG: Reranking for Bias Mitigation in Retrieval-Augmented Generation
[13] T Zhang et al., Evaluating the Effect of Retrieval Augmentation on Social Biases
[14] L et al., Lost in the Middle: How Language Models Use Long Contexts
[15] T E Kim et al., Towards fair rag: On the impact of fair ranking in retrieval-augmented generation
[16] M Dehghan, G McDonald, Who benefits from rag? the role of exposure, utility and attribution bias
[17] M Zehlike et al., FAIR: A fair top-k ranking algorithm
[18] M Zehlike et al., Reducing Disparate Exposure in Ranking: A Learning To Rank Approach
[19] Beutel et al., Fairness in Recommendation Ranking through Pairwise Comparisons
[20] A Singh, T Joachims, Policy Learning for Fairness in Ranking
[21] Linear Programming, in: Optimization Techniques and Applications with Examples
[22] H W Kuhn, The Hungarian method for the assignment problem (1955)
[23] S Fulay et al., On the relationship between truth and political bias in language models
[24] Y Zhao et al., A dataset generation method for bias evaluation in retrieval-augmented generation
[25] A Grattafiori et al., The Llama 3 Herd of Models
[26] Gemma Team, Gemma 2: Improving Open Language Models at a Practical Size
[27] A Q Jiang et al., Mistral 7B
[28] A Yang et al., Qwen2 Technical Report
[29] T Roelleke, J Wang, TF-IDF uncovered: A study of theories and probabilities
[30] S Robertson, H Zaragoza, The Probabilistic Relevance Framework: BM25 and Beyond
[31] T Formal et al., Splade: Sparse lexical and expansion model for first stage ranking
[32] J Chen et al., M3-embedding: Multi-linguality, multi-functionality, multigranularity text embeddings through self-knowledge distillation
[33] Z Li et al., Towards General Text Embeddings with Multi-stage Contrastive Learning
[34] M Douze et al., The Faiss library
[35] P Virtanen et al., Scipy 1.0: Fundamental algorithms for scientific computing in python
[38] [No page number provided for the reference list entries, using the context of the paper's structure.]
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
Controlled Bias Injection via Reranking: The system can achieve precise manipulation of embedding bias without modifying the underlying retriever by partitioning knowledge bases into group-specific subsets and using a probabilistic reranker to select and order documents for each question.
-
Position-Aware Bias Propagation Modeling: The system can model how bias at different retrieval positions influences the final output by fitting a linear regression model to data generated from controlled perturbations of position-wise embedding bias, capturing
how bias at different positions contributes to the generated output.
-
Fairness-Aware Retrieval Optimization using FARO: The system can balance relevance and fairness by treating fairness as an optimization problem and utilizing the Quadratic Fairness via Dual Hyperplane Approximation (FARO) framework, which decomposes the globally coupled problem into independent per-question subproblems for efficient computation.
-
Dynamic Trade-off Exploration: The FARO framework allows for
flexible exploration of the relevance–fairness trade-off
by enumerating a set of surrogate parameters mu, enabling practitioners to balance computational efficiency and solution quality across different scenarios.
Abstract
Retrieval-Augmented Generation (RAG) grounds large language models (LLMs) in external knowledge, but the retrieved documents can systematically skew generated answers toward one group. This effect is difficult to analyze and control in top-k settings, where several documents at different context positions jointly shape the output. We present a three-stage framework for fairness-aware retrieval in top-k RAG. First, a probabilistic reranker sets the group composition of the retrieved context at each position, enabling controlled perturbation of retrieval bias without modifying the retriever. Second, we show that output bias is well approximated by a position-weighted linear function of position-wise retrieval bias, revealing model-specific positional sensitivities. Third, we use this model to formulate retrieval as an optimization problem that trades off relevance against predicted output bias, and propose FARO, a scalable solution to that problem which decomposes the globally coupled quadratic objective into independent per-query assignment problems through a Fenchel--Legendre dual reformulation. Experiments with four open LLMs, and political and gender bias as use cases show that the linear model predicts output bias on unseen configurations in 17 of 24 settings. FARO substantially reduces output bias in most settings, while, compared with a linear-programming baseline, FARO achieves similar relevance, remains feasible where the baseline does not, and scales better to larger query sets and candidate pools.
Sources
- Scaling Laws for Neural Language Models
- No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
- A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions
- Evaluating the Effect of Retrieval Augmentation on Social Biases
- The Llama 3 Herd of Models
- Gemma 2: Improving Open Language Models at a Practical Size
- Mistral 7B
- Qwen2 Technical Report
- Towards General Text Embeddings with Multi-stage Contrastive Learning
- The Faiss library
Related papers
- Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
- Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- Samyama: A Unified Graph-Vector Database with In-Database Optimization, Agentic Enrichment, and Hardware Acceleration
- GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
- Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs