English
Related papers

Related papers: From Indirect Object Identification to Syllogisms:…

200 papers

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

The impressive ability of large language models to generate natural text across various tasks has led to critical challenges in authorship authentication. Although numerous detection methods have been developed to differentiate between…

Computation and Language · Computer Science 2025-05-20 Xu Zheng , Zhuomin Chen , Esteban Schafir , Sipeng Chen , Hojat Allah Salehi , Haifeng Chen , Farhad Shirani , Wei Cheng , Dongsheng Luo

Multimodal large language models (MLLMs) have demonstrated extraordinary capabilities in conducting conversations based on image inputs. However, we observe that MLLMs exhibit a pronounced form of visual sycophantic behavior. While similar…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Renjie Pi , Kehao Miao , Li Peihang , Runtao Liu , Jiahui Gao , Jipeng Zhang , Xiaofang Zhou

A mechanistic understanding of how MLPs do computation in deep neural networks remains elusive. Current interpretability work can extract features from hidden activations over an input dataset but generally cannot explain how MLP weights…

Machine Learning · Computer Science 2025-06-26 Michael T. Pearce , Thomas Dooms , Alice Rigg , Jose M. Oramas , Lee Sharkey

Large Language Models show promise in emotion understanding, social reasoning, and empathy, yet they struggle with psychologically grounded tasks that require inferring implicit mental states in context-rich, ambiguous settings. These…

Databases · Computer Science 2025-11-13 Yichao Feng , Haoran Luo , Lang Feng , Shuai Zhao , Anh Tuan Luu

The handling of probabilities in the form of uncertainty or partial information is an essential task for LLMs in many settings and applications. A common approach to evaluate an LLM's probabilistic reasoning capabilities is to assess its…

Artificial Intelligence · Computer Science 2026-02-12 Manuel Mondal , Ljiljana Dolamic , Gérôme Bovet , Philippe Cudré-Mauroux , Julien Audiffren

Large language models (LLMs) are effective at answering questions that are clearly asked. However, when faced with ambiguous queries they can act unpredictably and produce incorrect outputs. This underscores the need for the development of…

Computation and Language · Computer Science 2024-02-22 Yizhe Zhang , Jiarui Lu , Navdeep Jaitly

Recent studies on Learning to Optimize (L2O) suggest a promising path to automating and accelerating the optimization procedure for complicated tasks. Existing L2O models parameterize optimization rules by neural networks, and learn those…

Machine Learning · Computer Science 2022-05-10 Wenqing Zheng , Tianlong Chen , Ting-Kuei Hu , Zhangyang Wang

We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods.…

Computation and Language · Computer Science 2026-05-28 Nora Graichen , Iria de-Dios-Flores , Gemma Boleda

In order to predict the next token, LLMs must represent semantic and surface-level information about the current word. Previous work identified two types of attention heads that disentangle this information: (i) Concept induction heads,…

Computation and Language · Computer Science 2025-11-25 Sheridan Feucht , Byron Wallace , David Bau

Recent reasoning LLMs (RLMs), especially those trained with verifier-based reinforcement learning, often perform worse with few-shot CoT than with direct answering. We revisit this paradox using high-quality reasoning traces from…

Computation and Language · Computer Science 2025-09-30 Haonan Wang , Weida Liang , Zihang Fu , Nie Zheng , Yifan Zhang , Yao Tong , Tongyao Zhu , Hao Jiang , Chuang Li , Jiaying Wu , Kenji Kawaguchi

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

Multilingual large language models (LLMs) often exhibit factual inconsistencies across languages, with significantly better performance in factual recall tasks in English than in other languages. The causes of these failures, however,…

Computation and Language · Computer Science 2025-05-29 Meng Lu , Ruochen Zhang , Carsten Eickhoff , Ellie Pavlick

Modern task-oriented semantic parsing approaches typically use seq2seq transformers to map textual utterances to semantic frames comprised of intents and slots. While these models are empirically strong, their specific strengths and…

Computation and Language · Computer Science 2021-05-31 Shrey Desai , Ahmed Aly

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…

Computation and Language · Computer Science 2019-06-20 Jesse Vig , Yonatan Belinkov

Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activations. Specifically, recent studies have explored subspace…

Machine Learning · Computer Science 2023-12-07 Aleksandar Makelov , Georg Lange , Neel Nanda

Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues faces challenges: limited training data, annotation…

Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly with a small…

Computation and Language · Computer Science 2024-08-30 Emmy Liu , Graham Neubig , Jacob Andreas

Large Language Models (LLMs), powered by Transformers, have demonstrated human-like intelligence capabilities, yet their underlying mechanisms remain poorly understood. This paper presents a novel framework for interpreting LLMs as…

Computation and Language · Computer Science 2025-04-16 Phill Kyu Rhee

This study explores the explainability capabilities of large language models (LLMs), when employed to autonomously generate machine learning (ML) solutions. We examine two classification tasks: (i) a binary classification problem focused on…