# Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style

arXiv: https://arxiv.org/abs/2409.10955 · HTML: https://mlsanity.com/paper/2409.10955/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 17 Sep 2024.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 28 of 28)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [Large Language Models with Controllable Working Memory](https://mlsanity.com/paper/2211.05110/) (2022)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering](https://mlsanity.com/paper/2211.05655/) (2022)
- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024)
- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [What Evidence Do Language Models Find Convincing?](https://mlsanity.com/paper/2402.11782/) (2024)
- [BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief](https://mlsanity.com/paper/2109.14723/) (2021)
- [Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method](https://mlsanity.com/paper/2310.17918/) (2023)
- [BioRAG: A RAG-LLM Framework for Biological Question Reasoning](https://mlsanity.com/paper/2408.01107/) (2024)
- [Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP](https://mlsanity.com/paper/2106.06830/) (2021)
- [Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis](https://mlsanity.com/paper/2205.03784/) (2022)
- [Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning](https://mlsanity.com/paper/2204.09589/) (2022)
- [From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries](https://mlsanity.com/paper/2406.12824/) (2024)
- [Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction](https://mlsanity.com/paper/2210.04992/) (2022)
- [Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach](https://mlsanity.com/paper/2402.14948/) (2024)

## Built on by (most cited first, 11 of 11)

- [Context-DPO: Aligning Language Models for Context-Faithfulness](https://mlsanity.com/paper/2412.15280/) (2024)
- [Can LLMs Introspect? A Reality Check](https://mlsanity.com/paper/2605.26242/) (2026)
- [Learning When to Trust via Selective Context Preference Optimization](https://mlsanity.com/paper/2608.06377/) (2026)
- [Copy-Paste to Mitigate Large Language Model Hallucinations](https://mlsanity.com/paper/2510.00508/) (2025)
- [Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN](https://mlsanity.com/paper/2603.15892/) (2026)
- [Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models](https://mlsanity.com/paper/2606.05161/) (2026)
- [Plans for Evaluating Structured Generative Search Summaries](https://mlsanity.com/paper/2605.26400/) (2026)
- [CARE-MH: Towards Unified, Reproducible, and Comparable Evaluation of Mental Health LLMs](https://mlsanity.com/paper/2607.24754/) (2026)
- [DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial](https://mlsanity.com/paper/2608.02678/) (2026)
- [Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs](https://mlsanity.com/paper/2609.25602/) (2026)
- [Characterizing Overconfident Failure in LLM-Based Code Generation](https://mlsanity.com/paper/2610.11300/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context faithfulness remain largely unexplored. In this study, we investigate the impact of memory strength and evidence presentation on LLMs' receptiveness to external evidence. We quantify the memory strength of LLMs by measuring the divergence in LLMs' responses to different paraphrases of the same question, which is not considered by previous works. We also generate evidence in various styles to examine LLMs' behavior. Our results show that for questions with high memory strength, LLMs are more likely to rely on internal memory. Furthermore, presenting paraphrased evidence significantly increases LLMs' receptiveness compared to simple repetition or adding details. These findings provide key insights for improving retrieval-augmented generation and context-aware LLMs. Our code is available at https://github.com/liyp0095/ContextFaithful.