From Evidence to Judgment: Trace-Augmented Reasoning under Conflicting Evidence
cs.CL, cs.AI, cs.CY, cs.IR
Submitted: 2025-12-18
Updated: 2026-11-14
Code: https://github.com/ShubhamX90/reasoning-in-rag
Terminology
Sources
- Improving language models by retrieving from trillions of tokens
- SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
- QLoRA: Efficient Finetuning of Quantized LLMs
- A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
- Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Mistral 7B
- Open Domain Question Answering with Conflicting Contexts
- GPT-4o System Card
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
- ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
- ALiiCE: Evaluating Positional Fine-grained Citation Generation
- Qwen3 Technical Report
- SituatedQA: Incorporating Extra-Linguistic Contexts into QA
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data