Personas as a Way to Model Truthfulness in Language Models

• URL: http://arxiv.org/abs/2310.18168v5
• Date: Tue, 6 Feb 2024 09:04:04 GMT
• Title: Personas as a Way to Model Truthfulness in Language Models
• Authors: Nitish Joshi, Javier Rando, Abulhair Saparov, Najoung Kim, He He
• Abstract summary: 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.
• Score: 23.86655844340011
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are trained on vast amounts of text from the internet, which contains both factual and misleading information about the world. While unintuitive from a classic view of LMs, recent work has shown that the truth value of a statement can be elicited from the model's representations. This paper presents an explanation for why LMs appear to know the truth despite not being trained with truth labels. We hypothesize that the pretraining data is generated by groups of (un)truthful agents whose outputs share common features, and they form a (un)truthful persona. By training on this data, LMs can infer and represent the persona in its activation space. This allows the model to separate truth from falsehoods and controls the truthfulness of its generation. We show evidence for the persona hypothesis via two observations: (1) we can probe whether a model's answer will be truthful before it is generated; (2) finetuning a model on a set of facts improves its truthfulness on unseen topics. Next, using arithmetics as a synthetic environment, we show that structures of the pretraining data are crucial for the model to infer the truthful persona. Overall, our findings suggest that models can exploit hierarchical structures in the data to learn abstract concepts like truthfulness.

Related papers

• Training Language Models to Explain Their Own Computations [73.8562596518326]
  We study the extent to which LMs' privileged access to their own internals can be leveraged to produce new techniques for explaining their behavior.<n>Using existing interpretability techniques as a source of ground truth, we fine-tune LMs to generate natural language descriptions of (1) the information encoded by LM features, (2) the causal structure of LMs' internal activations, and (3) the influence of specific input tokens on LM outputs.
  arXiv  Detail & Related papers  (2025-11-11T18:57:14Z)
• Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning [11.28752240109815]
  Large language models continually evolve through pre-training on ever-expanding web data.<n>This adaptive process also exposes them to subtle forms of misinformation.<n>We investigate whether repeated exposure to false but confidently stated facts can shift a model's internal representation away from the truth.
  arXiv  Detail & Related papers  (2025-10-29T14:35:03Z)
• 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)
• Synthetic Data and the Shifting Ground of Truth [3.4858077573471107]
  This paper examines how ML researchers and practitioners bootstrap ground truth without relying on the stable ground of representation and real-world reference.<n>It will also reflect on the broader implications of a shift from a representational to what could be described as a mimetic or iconic concept of data.
  arXiv  Detail & Related papers  (2025-09-14T14:35:11Z)
• 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)
• How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence [52.9442657690445]
  Post-training is essential for the success of large language models (LLMs)<n>We compare base and post-trained LLMs from four perspectives to better understand post-training effects.
  arXiv  Detail & Related papers  (2025-04-03T06:30:55Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [79.01538178959726]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence. We introduce a novel generative model that generates tokens on the basis of human interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• MuLan: A Study of Fact Mutability in Language Models [50.626787909759976]
  Trustworthy language models ideally identify mutable facts as such and process them accordingly. We create MuLan, a benchmark for evaluating the ability of English language models to anticipate time-contingency.
  arXiv  Detail & Related papers  (2024-04-03T19:47:33Z)
• 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)
• Physics of Language Models: Part 3.2, Knowledge Manipulation [51.68385617116854]
  This paper investigates four fundamental knowledge manipulation tasks. We show that language models excel in knowledge retrieval but struggle even in the simplest classification or comparison tasks. Our findings also apply to modern pretrained language models such as GPT-4.
  arXiv  Detail & Related papers  (2023-09-25T17:50:41Z)
• Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models [27.943334687742244]
  We show that even the most advanced GPT models struggle to reason on manipulated facts. Our findings have practical implications for understanding the performance of LLMs in real-world applications.
  arXiv  Detail & Related papers  (2023-05-23T20:26:03Z)
• Discovering Latent Knowledge in Language Models Without Supervision [72.95136739040676]
  Existing techniques for training language models can be misaligned with the truth. We propose directly finding latent knowledge inside the internal activations of a language model in a purely unsupervised way. We show that despite using no supervision and no model outputs, our method can recover diverse knowledge represented in large language models.
  arXiv  Detail & Related papers  (2022-12-07T18:17:56Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• FaVIQ: FAct Verification from Information-seeking Questions [77.7067957445298]
  We construct a large-scale fact verification dataset called FaVIQ using information-seeking questions posed by real users. Our claims are verified to be natural, contain little lexical bias, and require a complete understanding of the evidence for verification.
  arXiv  Detail & Related papers  (2021-07-05T17:31:44Z)
• Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge [38.48518306055536]
  We develop a neural language model that includes an explicit interface between symbolically interpretable factual information and subsymbolic neural knowledge. We show that this model dramatically improves performance on two knowledge-intensive question-answering tasks.
  arXiv  Detail & Related papers  (2020-07-02T03:05:41Z)
• Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge [96.92252296244233]
  Large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. We show that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements. Our work paves a path towards open-domain systems that constantly improve by interacting with users who can instantly correct a model by adding simple natural language statements.
  arXiv  Detail & Related papers  (2020-06-11T17:02:20Z)

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.