English
Related papers

Related papers: Truth Neurons

200 papers

Large language models (LLMs) have demonstrated impressive capabilities across a variety of tasks, but their increasing autonomy in real-world applications raises concerns about their trustworthiness. While hallucinations-unintentional…

Machine Learning · Computer Science 2025-09-04 Haoran Huan , Mihir Prabhudesai , Mengning Wu , Shantanu Jaiswal , Deepak Pathak

Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…

Computation and Language · Computer Science 2026-04-07 Konstantin Krestnikov

How do language models retrieve entity-specific facts from their parameters? We investigate this question by searching for sparse, entity-selective MLP neurons - which we call entity cells, by analogy to the "grandmother cell" hypothesis in…

Computation and Language · Computer Science 2026-05-19 Itay Yona , Dan Barzilay , Michael Karasik , Mor Geva

Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona. These models are trained with fully supervised learning where the…

Computation and Language · Computer Science 2021-02-16 Mohsen Mesgar , Edwin Simpson , Iryna Gurevych

Language models (LMs) can exhibit human-like behaviour, but it is unclear how to describe this behaviour without undue anthropomorphism. We formalise a behaviourist view of LM character traits: qualities such as truthfulness, sycophancy, or…

Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks, enabled by multi-step reasoning induced using reinforcement learning. However, like previous language models, reasoning models are prone to…

Artificial Intelligence · Computer Science 2025-07-21 Zhiting Mei , Christina Zhang , Tenny Yin , Justin Lidard , Ola Shorinwa , Anirudha Majumdar

While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investigate this question using a novel dataset of realistic moral…

Despite the great success of large language models (LLMs) in various tasks, they suffer from generating hallucinations. We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using…

Computation and Language · Computer Science 2024-01-19 Zhongzhi Chen , Xingwu Sun , Xianfeng Jiao , Fengzong Lian , Zhanhui Kang , Di Wang , Cheng-Zhong Xu

Large language models (LLMs) have been shown to possess impressive capabilities, while also raising crucial concerns about the faithfulness of their responses. A primary issue arising in this context is the management of (un)answerable…

Computation and Language · Computer Science 2023-11-14 Aviv Slobodkin , Omer Goldman , Avi Caciularu , Ido Dagan , Shauli Ravfogel

Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM's confidence over facts. However, due to the lack of a…

Computation and Language · Computer Science 2024-11-28 Matéo Mahaut , Laura Aina , Paula Czarnowska , Momchil Hardalov , Thomas Müller , Lluís Màrquez

The nouns of our language refer to either concrete entities (like a table) or abstract concepts (like justice or love), and cognitive psychology has established that concreteness influences how words are processed. Accordingly,…

Computation and Language · Computer Science 2025-05-22 Cosimo Iaia , Bhavin Choksi , Emily Wiebers , Gemma Roig , Christian J. Fiebach

We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascent thesis proposes that facts are recalled from the training…

Computation and Language · Computer Science 2024-05-07 Jingcheng Niu , Andrew Liu , Zining Zhu , Gerald Penn

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

Machine Learning · Computer Science 2023-11-02 Fabien Roger , Ryan Greenblatt

There have been many studies on analyzing self-supervised speech Transformers, in particular, with layer-wise analysis. It is, however, desirable to have an approach that can pinpoint exactly a subset of neurons that is responsible for a…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-23 Tzu-Quan Lin , Guan-Ting Lin , Hung-yi Lee , Hao Tang

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

Computation and Language · Computer Science 2025-03-18 Alihan Hüyük , Xinnuo Xu , Jacqueline Maasch , Aditya V. Nori , Javier González

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on…

Computation and Language · Computer Science 2025-11-27 Yixiu Zhao , Xiaozhi Wang , Zijun Yao , Lei Hou , Juanzi Li

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

Artificial Intelligence · Computer Science 2026-05-12 Xiangkun Sun , Lingkai Kong , Aoqi Zhang , Liang Zeng , Tonghan Wang

While feed-forward neurons in pre-trained language models (PLMs) can encode knowledge, past research targeted a small subset of neurons that heavily influence outputs. This leaves the broader role of neuron activations unclear, limiting…

Computation and Language · Computer Science 2025-06-03 Xin Zhao , Zehui Jiang , Naoki Yoshinaga

The veracity of a factoid is largely independent of the language it is written in. However, language models are inconsistent in their ability to answer the same factual question across languages. This raises questions about how LLMs…

Computation and Language · Computer Science 2024-08-21 Maxim Ifergan , Leshem Choshen , Roee Aharoni , Idan Szpektor , Omri Abend

Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings. However, these models make confident mispredictions and produce unstable output, making them risky for factual and…

Artificial Intelligence · Computer Science 2026-04-07 Adeyemi Adeseye , Aisvarya Adeseye , Hannu Tenhunen , Jouni Isoaho
‹ Prev 1 3 4 5 6 7 10 Next ›