# Information Discernment in Large Language Models

arXiv: https://arxiv.org/abs/2607.19355 · HTML: https://mlsanity.com/paper/2607.19355/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 24 of 24)

- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [On the Risk of Misinformation Pollution with Large Language Models](https://mlsanity.com/paper/2305.13661/) (2023)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [What Large Language Models Know and What People Think They Know](https://mlsanity.com/paper/2401.13835/) (2024)
- [Combating Misinformation in the Age of LLMs: Opportunities and Challenges](https://mlsanity.com/paper/2311.05656/) (2023)
- [FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"](https://mlsanity.com/paper/2410.03727/) (2024)
- [Context-faithful Prompting for Large Language Models](https://mlsanity.com/paper/2303.11315/) (2023)
- [The spread of low-credibility content by social bots](https://mlsanity.com/paper/1707.07592/) (2017)
- [Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models](https://mlsanity.com/paper/2410.07176/) (2024)
- [WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia](https://mlsanity.com/paper/2406.13805/) (2024)
- [MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.00332/) (2024)
- [Attacking Open-domain Question Answering by Injecting Misinformation](https://mlsanity.com/paper/2110.07803/) (2021)
- [Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents](https://mlsanity.com/paper/2404.16032/) (2024)
- [Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models](https://mlsanity.com/paper/2304.00228/) (2023)
- [Who's Who: Large Language Models Meet Knowledge Conflicts in Practice](https://mlsanity.com/paper/2410.15737/) (2024)
- [Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences](https://mlsanity.com/paper/2511.02109/) (2025)
- [Evaluation of Reliability Criteria for News Publishers with Large Language Models](https://mlsanity.com/paper/2412.15896/) (2024)

## Built on by (most cited first, 1 of 1)

- [Resist, Update, Reject: Preference Optimization Installs a Prior-Dependent Reliability Switch](https://mlsanity.com/paper/2609.22359/) (2026)

## Abstract (arXiv)

LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating more for reliable sources (source discernment) and more when claims bring priors closer to the truth (truth discernment)? We formalize this as information discernment and introduce Learn2Discern (L2D), an experimental framework and benchmark grounded in three normative axioms with interpretable metrics. To establish external validity, a pre-registered, quota-matched user study (n=299) confirms that real LLM users endorse all three axioms and report that violations reduce their trust and usage intent. Across 13 models and nearly 670K trials, we find consistent failures across both dimensions: models perform near chance on source and truth discernment, rely on source popularity twice as much as source reliability, and update roughly equally whether a claim improves or worsens their position relative to the ground truth. Models integrate external knowledge most effectively on datasets where their priors are already the most accurate. Newer and larger models improve truth discernment but not source discernment, a blind spot that model complexity does not address. We identify simple inference-time interventions that improve both forms of discernment. We release our dataset and survey as a testbed for a core alignment property that scales in importance as LLMs replace traditional search.