English
Related papers

Related papers: Overthinking the Truth: Understanding how Language…

200 papers

Prior work on in-context copying has shown the existence of induction heads, which attend to and promote individual tokens during copying. In this work we discover a new type of induction head: concept-level induction heads, which copy…

Computation and Language · Computer Science 2025-07-22 Sheridan Feucht , Eric Todd , Byron Wallace , David Bau

Large Language Models (LLMs) often exhibit sycophantic behavior, agreeing with user-stated opinions even when those contradict factual knowledge. While prior work has documented this tendency, the internal mechanisms that enable such…

Computation and Language · Computer Science 2025-11-13 Keyu Wang , Jin Li , Shu Yang , Zhuoran Zhang , Di Wang

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…

Computation and Language · Computer Science 2024-05-09 Rafael Rivera Soto , Kailin Koch , Aleem Khan , Barry Chen , Marcus Bishop , Nicholas Andrews

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Computation and Language · Computer Science 2024-08-30 Tian Ye , Zicheng Xu , Yuanzhi Li , Zeyuan Allen-Zhu

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

The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains. One important problem class that has remained relatively…

Language models are increasingly capable, yet still fail at a seemingly simple task of multi-digit multiplication. In this work, we study why, by reverse-engineering a model that successfully learns multiplication via \emph{implicit…

Machine Learning · Computer Science 2025-10-02 Xiaoyan Bai , Itamar Pres , Yuntian Deng , Chenhao Tan , Stuart Shieber , Fernanda Viégas , Martin Wattenberg , Andrew Lee

Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…

Computation and Language · Computer Science 2025-09-17 Yongjian Tang , Doruk Tuncel , Christian Koerner , Thomas Runkler

Neural language models exhibit impressive performance on a variety of tasks, but their internal reasoning may be difficult to understand. Prior art aims to uncover meaningful properties within model representations via probes, but it is…

Computation and Language · Computer Science 2021-09-21 Mycal Tucker , Peng Qian , Roger Levy

Grasping the commonsense properties of everyday concepts is an important prerequisite to language understanding. While contextualised language models are reportedly capable of predicting such commonsense properties with human-level…

Computation and Language · Computer Science 2022-10-07 Amit Gajbhiye , Luis Espinosa-Anke , Steven Schockaert

Large language models are successful in answering factoid questions but are also prone to hallucination. We investigate the phenomenon of LLMs possessing correct answer knowledge yet still hallucinating from the perspective of inference…

Computation and Language · Computer Science 2024-10-29 Che Jiang , Biqing Qi , Xiangyu Hong , Dayuan Fu , Yang Cheng , Fandong Meng , Mo Yu , Bowen Zhou , Jie Zhou

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

Computation and Language · Computer Science 2025-10-14 Jialu Du , Guiyang Hou , Yihui Fu , Chen Wu , Wenqi Zhang , Yongliang Shen , Weiming Lu

There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…

Graphics · Computer Science 2022-09-29 Michael Fischer , Tobias Ritschel

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

Machine Learning · Computer Science 2025-10-07 Hazel Kim , Tom A. Lamb , Adel Bibi , Philip Torr , Yarin Gal

Recent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem. In this work, we demonstrate that, despite its…

Computation and Language · Computer Science 2021-09-10 Prasetya Ajie Utama , Nafise Sadat Moosavi , Victor Sanh , Iryna Gurevych

Previous researches have shown that learning multiple representations for polysemous words can improve the performance of word embeddings on many tasks. However, this leads to another problem. Several vectors of a word may actually point to…

Computation and Language · Computer Science 2017-01-09 Haoyue Shi , Caihua Li , Junfeng Hu

How can pretrained language models (PLMs) learn factual knowledge from the training set? We investigate the two most important mechanisms: reasoning and memorization. Prior work has attempted to quantify the number of facts PLMs learn, but…

Computation and Language · Computer Science 2020-10-13 Nora Kassner , Benno Krojer , Hinrich Schütze

Illusions are entertaining, but they are also a useful diagnostic tool in cognitive science, philosophy, and neuroscience. A typical illusion shows a gap between how something "really is" and how something "appears to be", and this gap…

Neurons and Cognition · Quantitative Biology 2024-12-30 Tomer Ullman

To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural language to reason…

Computation and Language · Computer Science 2023-11-03 Yuntian Deng , Kiran Prasad , Roland Fernandez , Paul Smolensky , Vishrav Chaudhary , Stuart Shieber

Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate…

Machine Learning · Computer Science 2022-12-01 Patrick Fernandes , Marcos Treviso , Danish Pruthi , André F. T. Martins , Graham Neubig