Language Models Encode the Contextual Truth of Propositions

• URL: http://arxiv.org/abs/2608.03035v1
• Date: Tue, 04 Aug 2026 02:30:59 GMT
• Title: Language Models Encode the Contextual Truth of Propositions
• Abstract summary: We show that contextual truth persists across structurally different output policies.<n>We find that propositions near the decision boundary are more susceptible to having their truth shifted through partner assertions.
• Score: 25.371554138996412
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Prior work has shown that LLMs encode the truth of factual propositions along linear directions in activation space. It's unclear how these representations extend to contextual truth: propositions whose truth is determined by in-context evidence rather than world knowledge. We show that LLMs maintain a linear representation of contextual truth that persists across structurally different output policies, even when the output doesn't require the model to determine a proposition's truth, and show causal evidence via steering experiments. Using the transcripts from a collaborative vision-language task that requires two LLMs to maintain a shared common ground, we show that truth representations of a proposition are significantly swayed by partner assertions about that proposition, even when the LLM has enough evidence to determine its truth. We find evidence that propositions near the decision boundary are more susceptible to having their truth shifted through partner assertions. Separating representation from output distinguish two forms of sycophancy that output behavior alone cannot: the model may accommodate a false proposition while continuing to represent it as false, or shift its representation across the boundary. The latter is 2.59x more common when the model agrees by restating the false claim explicitly than when it agrees implicitly.

Related papers

• Representational Stability of Truth in Large Language Models [0.15655985886975654]
  We introduce representational stability as the robustness of an LLM's veracity representations to perturbations in the operational definition of truth.<n>We compare two types of neither statements: fact-like assertions about entities we believe to be absent from any training data, and nonfactual claims drawn from well-known fictional contexts.<n>The unfamiliar statements induce the largest boundary shifts, producing up to $40%$ flipped truth in fragile domains.
  arXiv  Detail & Related papers  (2025-11-24T14:28:50Z)
• Emergence of Linear Truth Encodings in Language Models [64.86571541830598]
  Large language models exhibit linear subspaces that separate true from false statements, yet the mechanism behind their emergence is unclear.<n>We introduce a transparent, one-layer transformer toy model that reproduces such truth subspaces end-to-end.<n>We study one simple setting in which truth encoding can emerge, encouraging the model to learn this distinction in order to lower the LM loss on future tokens.
  arXiv  Detail & Related papers  (2025-10-17T16:30:07Z)
• Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs [29.9148172868873]
  Quantization enables efficient deployment of large language models (LLMs) in resource-constrained environments.<n>We introduce TruthfulnessEval, a comprehensive evaluation framework for assessing the truthfulness of quantized LLMs.<n>We find that while quantized models internally retain truthful representations, they are more susceptible to producing false outputs under misleading prompts.
  arXiv  Detail & Related papers  (2025-08-26T21:01:45Z)
• Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks [31.379237532476875]
  We investigate whether large language models (LLMs) encode truthfulness as a distinct linear feature, termed the "truth direction"<n>Our findings reveal that not all LLMs exhibit consistent truth directions, with stronger representations observed in more capable models.<n>We show that truthfulness probes trained on declarative atomic statements can generalize effectively to logical transformations, question-answering tasks, in-context learning, and external knowledge sources.
  arXiv  Detail & Related papers  (2025-06-01T03:55:53Z)
• Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs [48.202202256201815]
  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.
  arXiv  Detail & Related papers  (2025-05-22T11:00:53Z)
• On Reference (In-)Determinacy in Natural Language Inference [62.904689974282334]
  We revisit the reference determinacy (RD) assumption in the task of natural language inference (NLI)<n>We observe that current NLI models fail in downstream applications such as fact verification, where the input premise and hypothesis may refer to different contexts.<n>We introduce RefNLI, a diagnostic benchmark for identifying reference ambiguity in NLI examples.
  arXiv  Detail & Related papers  (2025-02-09T06:58:13Z)
• Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness? [53.98071556805525]
  Neural language models (LMs) can be used to evaluate the truth of factual statements. They can be queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these two procedures sometimes disagree, and that probes tend to be more accurate than LM outputs. This has led some researchers to conclude that LMs "lie" or otherwise encode non-cooperative communicative intents.
  arXiv  Detail & Related papers  (2023-11-27T18:59:14Z)
• Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs [95.07757789781213]
  Two lines of approaches are adopted for complex reasoning with LLMs.<n>One line of work prompts LLMs with various reasoning structures, while the structural outputs can be naturally regarded as intermediate reasoning steps.<n>The other line of work adopt LLM-free declarative solvers to do the reasoning task, rendering higher reasoning accuracy but lacking interpretability due to the black-box nature of the solvers.<n>We present a simple extension to the latter line of work. Specifically, we showcase that the intermediate search logs generated by Prolog interpreters can be accessed and interpreted into human-readable reasoning.
  arXiv  Detail & Related papers  (2023-11-16T11:26:21Z)
• Personas as a Way to Model Truthfulness in Language Models [23.86655844340011]
  Large language models (LLMs) are trained on vast amounts of text from the internet. This paper presents an explanation for why LMs appear to know the truth despite not being trained with truth labels.
  arXiv  Detail & Related papers  (2023-10-27T14:27:43Z)
• 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)
• AmbiFC: Fact-Checking Ambiguous Claims with Evidence [57.7091560922174]
  We present AmbiFC, a fact-checking dataset with 10k claims derived from real-world information needs. We analyze disagreements arising from ambiguity when comparing claims against evidence in AmbiFC. We develop models for predicting veracity handling this ambiguity via soft labels.
  arXiv  Detail & Related papers  (2021-04-01T17:40:08Z)

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.