Epistemic Diversity and Knowledge Collapse in Large Language Models

• URL: http://arxiv.org/abs/2510.04226v4
• Date: Thu, 30 Oct 2025 14:52:48 GMT
• Title: Epistemic Diversity and Knowledge Collapse in Large Language Models
• Abstract summary: Large language models (LLMs) tend to generate lexically, semantically, and stylistically homogenous texts.<n>This poses a risk of knowledge collapse, where homogenous LLMs mediate a shrinking in the range of accessible information over time.<n>We present a new methodology to measure epistemic diversity, i.e., variation in real-world claims in LLM outputs.
• Score: 42.81169404715417
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) tend to generate lexically, semantically, and stylistically homogenous texts. This poses a risk of knowledge collapse, where homogenous LLMs mediate a shrinking in the range of accessible information over time. Existing works on homogenization are limited by a focus on closed-ended multiple-choice setups or fuzzy semantic features, and do not look at trends across time and cultural contexts. To overcome this, we present a new methodology to measure epistemic diversity, i.e., variation in real-world claims in LLM outputs, which we use to perform a broad empirical study of LLM knowledge collapse. We test 27 LLMs, 155 topics covering 12 countries, and 200 prompt variations sourced from real user chats. For the topics in our study, we show that while newer models tend to generate more diverse claims, nearly all models are less epistemically diverse than a basic web search. We find that model size has a negative impact on epistemic diversity, while retrieval-augmented generation (RAG) has a positive impact, though the improvement from RAG varies by the cultural context. Finally, compared to a traditional knowledge source (Wikipedia), we find that country-specific claims reflect the English language more than the local one, highlighting a gap in epistemic representation

Related papers

• On Epistemic Diversity in Large Language Models [4.782109253713878]
  Large language models (LLMs) are increasingly used to answer questions, explain, teach, and support inquiry.<n>We argue that epistemic diversity is a useful evaluation dimension for settings where LLMs are used to support knowledge-intensive tasks.
  arXiv  Detail & Related papers  (2026-09-04T07:49:59Z)
• It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief [14.724790683440375]
  We introduce a typology to evaluate how different expressions of belief (EoBs) affect whether models follow context versus prior knowledge.<n>We generate controlled EoB-query pairs that isolate the effect of linguistic variation.<n>Our work reveals systematic patterns in how linguistic framing affects context integration, with implications for prompt engineering and model robustness.
  arXiv  Detail & Related papers  (2026-07-20T17:58:31Z)
• Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs [100.02824137397464]
  We investigate how Large Language Models adapt their internal representations when encountering inputs of increasing difficulty.<n>We reveal a consistent and quantifiable phenomenon: as task difficulty increases, the last hidden states of LLMs become substantially sparser.<n>This sparsity--difficulty relation is observable across diverse models and domains.
  arXiv  Detail & Related papers  (2026-03-03T18:48:15Z)
• The fragility of "cultural tendencies" in LLMs [23.77480663886995]
  We argue that the reported "cultural tendencies" are not stable traits but fragile artifacts of specific models and task design.<n>Our results show that prompt language has minimal effect on outputs, challenging LSZ's claim that these models encode grounded cultural beliefs.
  arXiv  Detail & Related papers  (2025-10-07T12:37:06Z)
• MLLMs are Deeply Affected by Modality Bias [158.64371871084478]
  Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integrating diverse modalities such as texts and images.<n>MLLMs are heavily influenced by modality bias, often relying on language while under-utilizing other modalities like visual inputs.<n>This paper argues that MLLMs are deeply affected by modality bias, highlighting its manifestations across various tasks.
  arXiv  Detail & Related papers  (2025-05-24T11:49:31Z)
• Multilingual Prompting for Improving LLM Generation Diversity [17.303344767549337]
  Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations.<n>We propose multilingual prompting: a prompting method which generates several variations of a base prompt with added cultural and linguistic cues from several cultures.
  arXiv  Detail & Related papers  (2025-05-21T07:59:21Z)
• Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English [66.97110551643722]
  We investigate dialectal disparities in Large Language Models (LLMs) reasoning tasks.<n>We find that LLMs produce less accurate responses and simpler reasoning chains and explanations for AAE inputs.<n>These findings highlight systematic differences in how LLMs process and reason about different language varieties.
  arXiv  Detail & Related papers  (2025-03-06T05:15:34Z)
• ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models [75.05436691700572]
  We introduce ExpliCa, a new dataset for evaluating Large Language Models (LLMs) in explicit causal reasoning.<n>We tested seven commercial and open-source LLMs on ExpliCa through prompting and perplexity-based metrics.<n>Surprisingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events.
  arXiv  Detail & Related papers  (2025-02-21T14:23:14Z)
• Large Language Models Reflect the Ideology of their Creators [71.65505524599888]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language.<n>This paper shows that the ideological stance of an LLM appears to reflect the worldview of its creators.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms [19.863120275409393]
  We create a diverse resource of recent English neologisms by using several popular collection methods. We analyze temporal drift using neologisms by comparing sentences containing new words with near-identical sentences that replace neologisms with existing substitute words. Model performance is nearly halved in machine translation when a single neologism is introduced in a sentence.
  arXiv  Detail & Related papers  (2024-02-19T16:19:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.