Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling

• URL: http://arxiv.org/abs/2505.21399v1
• Date: Tue, 27 May 2025 16:24:02 GMT
• Title: Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling
• Authors: Hovhannes Tamoyan, Subhabrata Dutta, Iryna Gurevych,
• Abstract summary: Factual incorrectness in generated content is one of the primary concerns in ubiquitous deployment of large language models (LLMs)<n>We provide evidence supporting the presence of LLMs' internal compass that dictate the correctness of factual recall at the time of generation.<n>Scaling experiments across model sizes and training dynamics highlight that self-awareness emerges rapidly during training and peaks in intermediate layers.
• Score: 56.26834106704781
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Factual incorrectness in generated content is one of the primary concerns in ubiquitous deployment of large language models (LLMs). Prior findings suggest LLMs can (sometimes) detect factual incorrectness in their generated content (i.e., fact-checking post-generation). In this work, we provide evidence supporting the presence of LLMs' internal compass that dictate the correctness of factual recall at the time of generation. We demonstrate that for a given subject entity and a relation, LLMs internally encode linear features in the Transformer's residual stream that dictate whether it will be able to recall the correct attribute (that forms a valid entity-relation-attribute triplet). This self-awareness signal is robust to minor formatting variations. We investigate the effects of context perturbation via different example selection strategies. Scaling experiments across model sizes and training dynamics highlight that self-awareness emerges rapidly during training and peaks in intermediate layers. These findings uncover intrinsic self-monitoring capabilities within LLMs, contributing to their interpretability and reliability.

Related papers

• LLMs as Repositories of Factual Knowledge: Limitations and Solutions [1.7764955091415962]
  We study the appropriateness of Large Language Models (LLMs) as repositories of factual knowledge.<n>We evaluate their reliability in responding to time-sensitive factual questions.<n>We propose "ENtity-Aware Fine-tuning" (ENAF) to improve the model's performance.
  arXiv  Detail & Related papers  (2025-01-22T10:16:53Z)
• Misinforming LLMs: vulnerabilities, challenges and opportunities [4.54019093815234]
  Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. This paper argues that current LLM architectures are inherently untrustworthy due to their reliance on correlations of sequential patterns of word embedding vectors. Research into combining generative transformer-based models with fact bases and logic programming languages may lead to the development of trustworthy LLMs.
  arXiv  Detail & Related papers  (2024-08-02T10:35:49Z)
• Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models [9.318796743761224]
  Despite growing interest in Theory of Mind (ToM) tasks for evaluating language models (LMs), little is known about how LMs internally represent mental states of self and others.<n>We present the first systematic investigation of belief representations in LMs by probing models across different scales, training regimens, and prompts.<n>Our experiments provide evidence that both model size and fine-tuning substantially improve LMs' internal representations of others' beliefs, which are structured - not mere by-products of spurious correlations - yet brittle to prompt variations.
  arXiv  Detail & Related papers  (2024-06-25T12:51:06Z)
• Large Language Models have Intrinsic Self-Correction Ability [18.79203446847577]
  Large language models (LLMs) have attracted significant attention for their exceptional abilities in various natural language processing tasks.<n>One promising solution to improve the LLMs' performance is to ask LLMs to revise their answer after generation.<n>In intrinsic self-correction is considered a promising direction because it does not utilize external knowledge.
  arXiv  Detail & Related papers  (2024-06-21T22:29:40Z)
• LLMs can learn self-restraint through iterative self-reflection [57.26854891567574]
  Large Language Models (LLMs) must be capable of dynamically adapting their behavior based on their level of knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach. We devise a utility function that can encourage the model to produce responses only when it is confident in them.
  arXiv  Detail & Related papers  (2024-05-15T13:35:43Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities.<n>If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information.<n>To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement [75.7148545929689]
  Large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We formally define LLM's self-bias - the tendency to favor its own generation. We analyze six LLMs on translation, constrained text generation, and mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-02-18T03:10:39Z)
• DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models [79.01926242857613]
  Large language models (LLMs) are prone to hallucinations, generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs. We find that this Decoding by Contrasting Layers (DoLa) approach is able to better surface factual knowledge and reduce the generation of incorrect facts.
  arXiv  Detail & Related papers  (2023-09-07T17:45:31Z)

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.