English
Related papers

Related papers: Truth Neurons

200 papers

Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to fully unlocking LLM's…

Computation and Language · Computer Science 2024-06-06 Shaolei Zhang , Tian Yu , Yang Feng

Natural language is an appealing medium for explaining how large language models process and store information, but evaluating the faithfulness of such explanations is challenging. To help address this, we develop two modes of evaluation…

Computation and Language · Computer Science 2023-09-20 Jing Huang , Atticus Geiger , Karel D'Oosterlinck , Zhengxuan Wu , Christopher Potts

When a language model is fed a wrong answer, what happens inside the network? Current understanding treats truthfulness as a static property of individual-layer representations-a direction to be probed, a feature to be extracted. Less is…

Computation and Language · Computer Science 2026-03-17 Javier Marín

Truthfulness (adherence to factual accuracy) and utility (satisfying human needs and instructions) are both fundamental aspects of Large Language Models, yet these goals often conflict (e.g., sell a car with known flaws), which makes it…

Artificial Intelligence · Computer Science 2025-04-29 Zhe Su , Xuhui Zhou , Sanketh Rangreji , Anubha Kabra , Julia Mendelsohn , Faeze Brahman , Maarten Sap

This paper introduces repetition neurons, regarded as skill neurons responsible for the repetition problem in text generation tasks. These neurons are progressively activated more strongly as repetition continues, indicating that they…

Computation and Language · Computer Science 2025-02-21 Tatsuya Hiraoka , Kentaro Inui

This work presents a framework for assessing whether large language models (LLMs) encode more factual knowledge in their parameters than what they express in their outputs. While a few studies hint at this possibility, none has clearly…

Computation and Language · Computer Science 2025-08-07 Zorik Gekhman , Eyal Ben David , Hadas Orgad , Eran Ofek , Yonatan Belinkov , Idan Szpektor , Jonathan Herzig , Roi Reichart

Can artificial intelligence unlock the secrets of the human brain? How do the inner mechanisms of deep learning models relate to our neural circuits? Is it possible to enhance AI by tapping into the power of brain recordings? These…

Neurons and Cognition · Quantitative Biology 2024-12-31 Subba Reddy Oota , Zijiao Chen , Manish Gupta , Raju S. Bapi , Gael Jobard , Frederic Alexandre , Xavier Hinaut

In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test…

Computation and Language · Computer Science 2020-11-13 Youmna Farag , Josef Valvoda , Helen Yannakoudakis , Ted Briscoe

The problem of estimating event truths from conflicting agent opinions in a social network is investigated. An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations. A Bayesian network…

Machine Learning · Computer Science 2021-01-26 Jielong Yang , Wee Peng Tay

Despite the effectiveness of large language models (LLMs) for code generation, they often output incorrect code. One reason is that model output probabilities are often not well-correlated with correctness, and reflect only the final output…

Software Engineering · Computer Science 2026-01-22 Francisco Ribeiro , Claudio Spiess , Prem Devanbu , Sarah Nadi

Multilingual language models (MLMs) store factual knowledge across languages but often struggle to provide consistent responses to semantically equivalent prompts in different languages. While previous studies point out this cross-lingual…

Computation and Language · Computer Science 2025-04-08 Mingyang Wang , Heike Adel , Lukas Lange , Yihong Liu , Ercong Nie , Jannik Strötgen , Hinrich Schütze

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

Computation and Language · Computer Science 2025-08-05 Rui Jiao , Yue Zhang , Jinku Li

We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs), which serves as a crucial step in building trust between humans and LLMs. Although several approaches based on entropy or…

Computation and Language · Computer Science 2024-02-29 Fan Yin , Jayanth Srinivasa , Kai-Wei Chang

Transformer-based pre-trained language models have demonstrated superior performance on various natural language processing tasks. However, it remains unclear how the skills required to handle these tasks distribute among model parameters.…

Computation and Language · Computer Science 2022-11-15 Xiaozhi Wang , Kaiyue Wen , Zhengyan Zhang , Lei Hou , Zhiyuan Liu , Juanzi Li

In this paper, we investigate whether Large Language Models (LLMs) actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks. Through an analysis of LLMs' internal factual recall at each…

Computation and Language · Computer Science 2024-10-02 Yifei Wang , Yuheng Chen , Wanting Wen , Yu Sheng , Linjing Li , Daniel Dajun Zeng

Large Language Models (LLMs) have revolutionised natural language processing, exhibiting impressive human-like capabilities. In particular, LLMs are capable of "lying", knowingly outputting false statements. Hence, it is of interest and…

Computation and Language · Computer Science 2024-10-22 Lennart Bürger , Fred A. Hamprecht , Boaz Nadler

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Artificial Intelligence · Computer Science 2026-01-22 Chongwen Zhao , Yutong Ke , Kaizhu Huang

Prior research demonstrates that performance of language models on reasoning tasks can be influenced by suggestions, hints and endorsements. However, the influence of endorsement source credibility remains underexplored. We investigate…

Computation and Language · Computer Science 2026-05-28 Priyanka Mary Mammen , Emil Joswin , Shankar Venkitachalam

As AI technologies are rolled out into healthcare, academia, human resources, law, and a multitude of other domains, they become de-facto arbiters of truth. But truth is highly contested, with many different definitions and approaches. This…

Computers and Society · Computer Science 2023-01-31 Luke Munn , Liam Magee , Vanicka Arora

We propose a general framework called Text Modular Networks(TMNs) for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvable by existing models. To ensure solvability of simpler…

Computation and Language · Computer Science 2021-04-14 Tushar Khot , Daniel Khashabi , Kyle Richardson , Peter Clark , Ashish Sabharwal