Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs

• URL: http://arxiv.org/abs/2505.16520v3
• Date: Fri, 30 May 2025 10:53:48 GMT
• Title: Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs
• Authors: Giovanni Servedio, Alessandro De Bellis, Dario Di Palma, Vito Walter Anelli, Tommaso Di Noia,
• Abstract summary: Factual hallucinations are a major challenge for Large Language Models (LLMs)<n>They undermine reliability and user trust by generating inaccurate or fabricated content.<n>Recent studies suggest that when generating false statements, the internal states of LLMs encode information about truthfulness.
• Score: 48.202202256201815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Factual hallucinations are a major challenge for Large Language Models (LLMs). They undermine reliability and user trust by generating inaccurate or fabricated content. Recent studies suggest that when generating false statements, the internal states of LLMs encode information about truthfulness. However, these studies often rely on synthetic datasets that lack realism, which limits generalization when evaluating the factual accuracy of text generated by the model itself. In this paper, we challenge the findings of previous work by investigating truthfulness encoding capabilities, leading to the generation of a more realistic and challenging dataset. Specifically, we extend previous work by introducing: (1) a strategy for sampling plausible true-false factoid sentences from tabular data and (2) a procedure for generating realistic, LLM-dependent true-false datasets from Question Answering collections. Our analysis of two open-source LLMs reveals that while the findings from previous studies are partially validated, generalization to LLM-generated datasets remains challenging. This study lays the groundwork for future research on factuality in LLMs and offers practical guidelines for more effective evaluation.

Related papers

• Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond [55.984684518346924]
  We recast Knowledge Tracing as an inverse problem: learning the minimum natural-language summary that makes past answers explainable and future answers predictable.<n>Our Language Bottleneck Model (LBM) consists of an encoder LLM that writes an interpretable knowledge summary and a frozen decoder LLM that must reconstruct and predict student responses using only that summary text.<n> Experiments on synthetic arithmetic benchmarks and the large-scale Eedi dataset show that LBMs rival the accuracy of state-of-the-art KT and direct LLM methods while requiring orders-of-magnitude fewer student trajectories.
  arXiv  Detail & Related papers  (2025-06-20T13:21:14Z)
• Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers [59.168391398830515]
  We evaluate 12 pre-trained LLMs and one specialized fact-verifier, using a collection of examples from 14 fact-checking benchmarks.<n>We highlight the importance of addressing annotation errors and ambiguity in datasets.<n> frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance.
  arXiv  Detail & Related papers  (2025-06-16T10:32:10Z)
• FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data [13.108807408880645]
  We propose a novel approach for synthetic data generation, CG2C, that leverages multi-hop reasoning on context graphs extracted from documents.<n>Our fact checker model, FactCG, demonstrates improved performance with more connected reasoning, using the same backbone models.
  arXiv  Detail & Related papers  (2025-01-28T18:45:07Z)
• Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis [78.07225438556203]
  We introduce LLM-Oasis, the largest resource for training end-to-end factuality evaluators.<n>It is constructed by extracting claims from Wikipedia, falsifying a subset of these claims, and generating pairs of factual and unfactual texts.<n>We then rely on human annotators to both validate the quality of our dataset and to create a gold standard test set for factuality evaluation systems.
  arXiv  Detail & Related papers  (2024-11-29T12:21:15Z)
• Knowing When to Ask -- Bridging Large Language Models and Data [3.111987311375933]
  Large Language Models (LLMs) are prone to generating factually incorrect information when responding to queries that involve numerical and statistical data or other timely facts. We present an approach for enhancing the accuracy of LLMs by integrating them with Data Commons.
  arXiv  Detail & Related papers  (2024-09-10T17:51:21Z)
• Robustness of LLMs to Perturbations in Text [2.0670689746336]
  Large language models (LLMs) have shown impressive performance, but can they handle the inevitable noise in real-world data? This work tackles this critical question by investigating LLMs' resilience against morphological variations in text. Our findings show that contrary to popular beliefs, generative LLMs are quiet robust to noisy perturbations in text.
  arXiv  Detail & Related papers  (2024-07-12T04:50:17Z)
• Understanding Privacy Risks of Embeddings Induced by Large Language Models [75.96257812857554]
  Large language models show early signs of artificial general intelligence but struggle with hallucinations. One promising solution is to store external knowledge as embeddings, aiding LLMs in retrieval-augmented generation. Recent studies experimentally showed that the original text can be partially reconstructed from text embeddings by pre-trained language models.
  arXiv  Detail & Related papers  (2024-04-25T13:10:48Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity [61.54815512469125]
  This survey addresses the crucial issue of factuality in Large Language Models (LLMs) As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital.
  arXiv  Detail & Related papers  (2023-10-11T14:18:03Z)
• The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets [6.732432949368421]
  Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the truth by training probes on the LLM's internal activations. We present evidence that at sufficient scale, LLMs linearly represent the truth or falsehood of factual statements.
  arXiv  Detail & Related papers  (2023-10-10T17:54:39Z)

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.