# Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?

arXiv: https://arxiv.org/abs/2401.11911 · HTML: https://mlsanity.com/paper/2401.11911/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 22 Jan 2024.

## Builds on (most cited first, 30 of 34)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [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)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2311.09210/) (2023)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation](https://mlsanity.com/paper/2307.11019/) (2023)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [On the Risk of Misinformation Pollution with Large Language Models](https://mlsanity.com/paper/2305.13661/) (2023)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering](https://mlsanity.com/paper/1908.08167/) (2019)

## Built on by (most cited first, 30 of 48)

- [Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs](https://mlsanity.com/paper/2510.17771/) (2025)
- [AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge](https://mlsanity.com/paper/2409.07394/) (2024)
- [Taming Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2503.10996/) (2025)
- [Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking](https://mlsanity.com/paper/2502.09083/) (2025)
- [FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.08938/) (2025)
- [DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs](https://mlsanity.com/paper/2506.08500/) (2025)
- [Your AI, Not Your View: The Bias of LLMs in Investment Analysis](https://mlsanity.com/paper/2507.20957/) (2025)
- [Pre-training Limited Memory Language Models with Internal and External Knowledge](https://mlsanity.com/paper/2505.15962/) (2025)
- [TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs](https://mlsanity.com/paper/2511.10375/) (2025)
- [Whose Facts Win? LLM Source Preferences under Knowledge Conflicts](https://mlsanity.com/paper/2601.03746/) (2026)
- [The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation](https://mlsanity.com/paper/2505.15807/) (2025)
- [CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models](https://mlsanity.com/paper/2508.17670/) (2025)
- [A Reality Check on Context Utilisation for Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.17031/) (2024)
- [Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems](https://mlsanity.com/paper/2511.01268/) (2025)
- [NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge](https://mlsanity.com/paper/2510.21144/) (2025)
- [Investigating Tool-Memory Conflicts in Tool-Augmented LLMs](https://mlsanity.com/paper/2601.09760/) (2026)
- [How does Misinformation Affect Large Language Model Behaviors and Preferences?](https://mlsanity.com/paper/2505.21608/) (2025)
- [Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models](https://mlsanity.com/paper/2508.19720/) (2025)
- [Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation](https://mlsanity.com/paper/2601.07506/) (2026)
- [CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy](https://mlsanity.com/paper/2508.01696/) (2025)
- [Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data](https://mlsanity.com/paper/2508.15793/) (2025)
- [GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?](https://mlsanity.com/paper/2602.06013/) (2026)
- [What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA](https://mlsanity.com/paper/2412.12632/) (2024)
- [KScope: A Framework for Characterizing the Knowledge Status of Language Models](https://mlsanity.com/paper/2506.07458/) (2025)
- [Conflicts in Texts: Data, Implications and Challenges](https://mlsanity.com/paper/2504.19472/) (2025)
- [Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation](https://mlsanity.com/paper/2412.18800/) (2024)
- [UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge](https://mlsanity.com/paper/2502.13648/) (2025)
- [SynDec: A Synthesize-then-Decode Approach for Arbitrary Textual Style Transfer via Large Language Models](https://mlsanity.com/paper/2505.12821/) (2025)
- [ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction](https://mlsanity.com/paper/2511.01188/) (2025)
- [When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models](https://mlsanity.com/paper/2601.07041/) (2026)

## Abstract (arXiv)

While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts generated by LLMs and those retrieved from external sources. To investigate this, we formulate a systematic framework to identify whether LLMs' responses are attributed to either generated or retrieved contexts. To easily trace the origin of the response, we construct datasets with conflicting contexts, i.e., each question is paired with both generated and retrieved contexts, yet only one of them contains the correct answer. Our experiments reveal a significant bias in several LLMs (GPT-4/3.5 and Llama2) to favor generated contexts, even when they provide incorrect information. We further identify two key factors contributing to this bias: i) contexts generated by LLMs typically show greater similarity to the questions, increasing their likelihood of being selected; ii) the segmentation process used in retrieved contexts disrupts their completeness, thereby hindering their full utilization in LLMs. Our analysis enhances the understanding of how LLMs merge diverse contexts, offers valuable insights for advancing current LLM augmentation methods, and highlights the risk of generated misinformation for retrieval-augmented LLMs.