English
Related papers

Related papers: Truth Neurons

200 papers

Perceived trustworthiness underpins how users navigate online information, yet it remains unclear whether large language models (LLMs),increasingly embedded in search, recommendation, and conversational systems, represent this construct in…

Artificial Intelligence · Computer Science 2026-01-19 Gerard Yeo , Svetlana Churina , Kokil Jaidka

As large language models (LLMs) advance in their linguistic capacity, understanding how they capture aspects of language competence remains a significant challenge. This study therefore employs psycholinguistic paradigms in English, which…

Computation and Language · Computer Science 2024-12-12 Xufeng Duan , Xinyu Zhou , Bei Xiao , Zhenguang G. Cai

Reliable uncertainty quantification is a first step towards building explainable, transparent, and accountable artificial intelligent systems. Recent progress in Bayesian deep learning has made such quantification realizable. In this paper,…

Computation and Language · Computer Science 2018-11-20 Yijun Xiao , William Yang Wang

Large language models pretrained on a huge amount of data capture rich knowledge and information in the training data. The ability of data memorization and regurgitation in pretrained language models, revealed in previous studies, brings…

Cryptography and Security · Computer Science 2023-12-06 Xinwei Wu , Junzhuo Li , Minghui Xu , Weilong Dong , Shuangzhi Wu , Chao Bian , Deyi Xiong

Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for…

Computation and Language · Computer Science 2025-10-07 Amir Hameed Mir

When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the…

Computation and Language · Computer Science 2025-11-07 Amir Zur , Atticus Geiger , Ekdeep Singh Lubana , Eric Bigelow

Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current…

Computation and Language · Computer Science 2024-09-30 Siheng Li , Cheng Yang , Taiqiang Wu , Chufan Shi , Yuji Zhang , Xinyu Zhu , Zesen Cheng , Deng Cai , Mo Yu , Lemao Liu , Jie Zhou , Yujiu Yang , Ngai Wong , Xixin Wu , Wai Lam

This study introduces a hypothesis-testing framework to assess whether large language models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We go beyond evaluating LLMs on accuracy; rather, we aim to…

Computation and Language · Computer Science 2024-10-07 Bowen Jiang , Yangxinyu Xie , Zhuoqun Hao , Xiaomeng Wang , Tanwi Mallick , Weijie J. Su , Camillo J. Taylor , Dan Roth

Mechanistic approaches to deception in large language models (LLMs) often rely on "lie detectors", that is, truth probes trained to identify internal representations of model outputs as false. The lie detector approach to LLM deception…

Computation and Language · Computer Science 2026-03-12 Tom-Felix Berger

Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it is imperative to develop algorithms to learn models with…

Machine Learning · Computer Science 2019-01-29 Yinpeng Dong , Fan Bao , Hang Su , Jun Zhu

We posit that large language models (LLMs) should be capable of expressing their intrinsic uncertainty in natural language. For example, if the LLM is equally likely to output two contradicting answers to the same question, then its…

Computation and Language · Computer Science 2024-09-27 Gal Yona , Roee Aharoni , Mor Geva

Analogical reasoning is at the core of human cognition, serving as an important foundation for a variety of intellectual activities. While prior work has shown that LLMs can represent task patterns and surface-level concepts, it remains…

Computation and Language · Computer Science 2025-11-26 Taewhoo Lee , Minju Song , Chanwoong Yoon , Jungwoo Park , Jaewoo Kang

Transformers for language modeling usually rely on deterministic internal computation, with uncertainty expressed mainly at the output layer. We introduce variational neurons into Transformer feed-forward computation so that uncertainty…

Machine Learning · Computer Science 2026-03-31 Yves Ruffenach

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Artificial Intelligence · Computer Science 2026-01-30 Jinhao Pan , Chahat Raj , Anjishnu Mukherjee , Sina Mansouri , Bowen Wei , Shloka Yada , Ziwei Zhu

Large Language Models have demonstrated impressive reasoning capabilities across multiple languages. However, the relationship between capabilities in different languages is less explored. In this work, we decompose the process of reasoning…

Computation and Language · Computer Science 2025-03-04 Peng Hu , Sizhe Liu , Changjiang Gao , Xin Huang , Xue Han , Junlan Feng , Chao Deng , Shujian Huang

Neuron Interpretation has gained traction in the field of interpretability, and have provided fine-grained insights into what a model learns and how language knowledge is distributed amongst its different components. However, the lack of…

Computation and Language · Computer Science 2023-11-07 Yimin Fan , Fahim Dalvi , Nadir Durrani , Hassan Sajjad

We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and…

Artificial Intelligence · Computer Science 2015-12-01 Jason Weston , Sumit Chopra , Antoine Bordes

Large language models (LLMs) have achieved a degree of success in generating coherent and contextually relevant text, yet they remain prone to a significant challenge known as hallucination: producing information that is not substantiated…

Computation and Language · Computer Science 2024-10-28 Ray Li , Tanishka Bagade , Kevin Martinez , Flora Yasmin , Grant Ayala , Michael Lam , Kevin Zhu

Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…

Software Engineering · Computer Science 2026-03-20 Zhe Yin , Xiaodong Gu , Beijun Shen

Language models (LMs) are said to be exhibiting reasoning, but what does this entail? We assess definitions of reasoning and how key papers in the field of natural language processing (NLP) use the notion and argue that the definitions…

Computation and Language · Computer Science 2025-11-18 Bertram Højer