A Triple-Robustness Analysis of Retrieval-Augmented Generation for Multi-Hop Requirements Traceability

arXiv:2608.00705 · cs.IR, cs.CL · Submitted 2026-08-01 · Read on arXiv

Meftun Akarsu, Burak Özdemir, Doğancan Büyükçolak, Recep Kaan Karaman

cs.IR, cs.CL

Submitted: 2026-08-01

Comments: 6 pages, 3 figures, 4 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Faithfulness — 33× in this paper · explained in 2 episodes
• RAG — 29× in this paper · explained in 3 episodes
• Robustness — 14× in this paper · explained in 6 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Generator — 4× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Composition — 1× in this paper · explained in 2 episodes
• Continual Learning — 1× in this paper · explained in 3 episodes
• European Union Aviation Safety Agency — 1× in this paper
• Generative AI — 1× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 1× in this paper
• LLM judge — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 4 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Query Complexity — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Universality — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
• When +1% Is Not Enough: A Paired Bootstrap Protocol for Evaluating Small Improvements
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Enabling Large Language Models to Generate Text with Citations
• LightRAG: Simple and Fast Retrieval-Augmented Generation
• From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
• RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
• Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks
• TVR: Automotive System Requirement Traceability Validation and Recovery Through Retrieval-Augmented Generation
• RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
• MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
• Correctness is not Faithfulness in RAG Attributions
• Self-Preference Bias in LLM-as-a-Judge
• When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation
• Corrective Retrieval Augmented Generation

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• QProtFuse: Query-Guided Layer Fusion for Retrieval-Augmented Protein Function Prediction
• DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?