Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks

• URL: http://arxiv.org/abs/2307.00175v1
• Date: Fri, 30 Jun 2023 23:44:51 GMT
• Title: Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks
• Abstract summary: We consider the questions of whether or not large language models (LLMs) have beliefs, and, if they do, how we might measure them. We evaluate two existing approaches, one due to Azaria and Mitchell (2023) and the other to Burns et al. (2022). We argue that, even if LLMs have beliefs, these methods are unlikely to be successful for conceptual reasons. Thus, there is still no lie-detector for LLMs.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We consider the questions of whether or not large language models (LLMs) have beliefs, and, if they do, how we might measure them. First, we evaluate two existing approaches, one due to Azaria and Mitchell (2023) and the other to Burns et al. (2022). We provide empirical results that show that these methods fail to generalize in very basic ways. We then argue that, even if LLMs have beliefs, these methods are unlikely to be successful for conceptual reasons. Thus, there is still no lie-detector for LLMs. After describing our empirical results we take a step back and consider whether or not we should expect LLMs to have something like beliefs in the first place. We consider some recent arguments aiming to show that LLMs cannot have beliefs. We show that these arguments are misguided. We provide a more productive framing of questions surrounding the status of beliefs in LLMs, and highlight the empirical nature of the problem. We conclude by suggesting some concrete paths for future work.

Related papers

• Incoherent Beliefs & Inconsistent Actions in Large Language Models [33.54139088666698]
  Real-world tasks and environments exhibit differences from the static datasets that large language models (LLMs) are typically evaluated on.<n>We examine two critical components of LLM performance: the ability of LLMs to coherently update their beliefs, and the extent to which the actions they take are consistent with those beliefs.<n>Our results highlight the difficulties of predicting LLM behavior in complex real-world settings.
  arXiv  Detail & Related papers  (2025-11-17T11:04:00Z)
• Unveiling Causal Reasoning in Large Language Models: Reality or Mirage? [62.17959154852391]
  Causal reasoning capability is critical in advancing large language models toward strong artificial intelligence.<n>We show that large language models (LLMs) are only capable of performing shallow (level-1) causal reasoning.<n>We propose G2-Reasoner, a method that incorporates general knowledge and goal-oriented prompts into LLMs' causal reasoning processes.
  arXiv  Detail & Related papers  (2025-06-26T13:11:01Z)
• Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations [0.8949668577519213]
  Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. These explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. We introduce a new approach for measuring the faithfulness of LLM explanations.
  arXiv  Detail & Related papers  (2025-04-19T02:51:20Z)
• Are LLMs Aware that Some Questions are not Open-ended? [58.93124686141781]
  We study whether Large Language Models are aware that some questions have limited answers and need to respond more deterministically. The lack of question awareness in LLMs leads to two phenomena: (1) too casual to answer non-open-ended questions or (2) too boring to answer open-ended questions.
  arXiv  Detail & Related papers  (2024-10-01T06:07:00Z)
• On the attribution of confidence to large language models [0.1478468781294373]
  Credences are mental states corresponding to degrees of confidence in propositions. The theoretical basis for credence attribution is unclear. It is a distinct possibility that even if LLMs have credences, credence attributions are generally false.
  arXiv  Detail & Related papers  (2024-07-11T10:51:06Z)
• Does ChatGPT Have a Mind? [0.0]
  This paper examines whether Large Language Models (LLMs) like ChatGPT possess minds, focusing specifically on whether they have a genuine folk psychology encompassing beliefs, desires, and intentions. First, we survey various philosophical theories of representation, including informational, causal, structural, and teleosemantic accounts, arguing that LLMs satisfy key conditions proposed by each. Second, we explore whether LLMs exhibit robust dispositions to perform actions, a necessary component of folk psychology.
  arXiv  Detail & Related papers  (2024-06-27T00:21:16Z)
• Dissecting the Ullman Variations with a SCALPEL: Why do LLMs fail at Trivial Alterations to the False Belief Task? [1.4936946857731093]
  We introduce SCALPEL: a technique to generate targeted modifications for False Belief tasks. We find that modifications which make explicit common inferences preserve LLMs' performance. This suggests that LLMs' failures on modified ToM tasks could result from a lack of more general commonsense reasoning.
  arXiv  Detail & Related papers  (2024-06-20T21:02:30Z)
• A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation [72.93327642336078]
  We propose Belief Tree Propagation (BTProp), a probabilistic framework for hallucination detection. BTProp introduces a belief tree of logically related statements by decomposing a parent statement into child statements. Our method improves baselines by 3%-9% (evaluated by AUROC and AUC-PR) on multiple hallucination detection benchmarks.
  arXiv  Detail & Related papers  (2024-06-11T05:21:37Z)
• A Comprehensive Evaluation on Event Reasoning of Large Language Models [68.28851233753856]
  How well LLMs accomplish event reasoning on various relations and reasoning paradigms remains unknown. We introduce a novel benchmark EV2 for EValuation of EVent reasoning. We find that LLMs have abilities to accomplish event reasoning but their performances are far from satisfactory.
  arXiv  Detail & Related papers  (2024-04-26T16:28:34Z)
• When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation [66.01754585188739]
  Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs' hallucinations. We propose several methods to enhance LLMs' perception of knowledge boundaries and show that they are effective in reducing overconfidence.
  arXiv  Detail & Related papers  (2024-02-18T04:57:19Z)
• Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination? [73.454943870226]
  This work studies a specific type of hallucination induced by semantic associations. To quantify this phenomenon, we propose a novel probing method and benchmark called EureQA.
  arXiv  Detail & Related papers  (2023-11-16T09:27:36Z)
• Position: Key Claims in LLM Research Have a Long Tail of Footnotes [81.14898541318198]
  We argue that we do not have a working definition of Large Language Models (LLMs) We critically examine five common claims regarding their properties. We conclude with suggestions for future research directions and their framing.
  arXiv  Detail & Related papers  (2023-08-14T13:00:53Z)
• Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate [19.887103433032774]
  Large language models (LLMs) have shown impressive performance in complex reasoning tasks. This work explores testing LLMs' reasoning by engaging with them in a debate-like conversation. We find that despite their impressive performance, LLMs like ChatGPT cannot maintain their beliefs in truth for a significant portion of examples.
  arXiv  Detail & Related papers  (2023-05-22T15:47:31Z)

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.