English
Related papers

Related papers: Inferring Functionality of Attention Heads from th…

200 papers

Large language models (LLMs) exhibit impressive in-context learning (ICL) capability, enabling them to perform new tasks using only a few demonstrations in the prompt. Two different mechanisms have been proposed to explain ICL: induction…

Machine Learning · Computer Science 2025-05-05 Kayo Yin , Jacob Steinhardt

Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evaluation is expensive, and LLM-as-judge approaches risk introducing hidden errors. Recent…

Attention is a powerful and ubiquitous mechanism for allowing neural models to focus on particular salient pieces of information by taking their weighted average when making predictions. In particular, multi-headed attention is a driving…

Computation and Language · Computer Science 2019-11-05 Paul Michel , Omer Levy , Graham Neubig

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…

Computation and Language · Computer Science 2025-06-19 Hao Chen , Haoze Li , Zhiqing Xiao , Lirong Gao , Qi Zhang , Xiaomeng Hu , Ningtao Wang , Xing Fu , Junbo Zhao

Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness, i.e.,…

Computation and Language · Computer Science 2024-12-13 Hanzhang Zhou , Zijian Feng , Zixiao Zhu , Junlang Qian , Kezhi Mao

Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possible approach to improve reasoning consistency is through activation steering. However,…

Machine Learning · Computer Science 2026-05-22 Ian Li , Kapilesh Guruprasad , Raunak Sengupta , Ninad Satish , Loris D'Antoni , Rose Yu

Mathematical reasoning in large language models (LMs) has garnered significant attention in recent work, but there is a limited understanding of how these models process and store information related to arithmetic tasks within their…

Computation and Language · Computer Science 2023-10-23 Alessandro Stolfo , Yonatan Belinkov , Mrinmaya Sachan

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks but remain prone to hallucinations. Detecting hallucinations is essential for safety-critical applications, and recent methods leverage attention map…

Machine Learning · Computer Science 2025-10-21 Jakub Binkowski , Denis Janiak , Albert Sawczyn , Bogdan Gabrys , Tomasz Kajdanowicz

LLMs' performance on complex tasks is still unsatisfactory. A key issue is that presently LLMs learn in a data-driven schema, while the instructions about these complex tasks are both scarce and hard to collect or construct. On the…

Machine Learning · Computer Science 2024-10-21 Yang Zhao , Li Du , Xiao Ding , Kai Xiong , Ting Liu , Bing Qin

Understanding the inner workings of large language models (LLMs) is crucial for advancing their theoretical foundations and real-world applications. While the attention mechanism and multi-layer perceptrons (MLPs) have been studied…

Computation and Language · Computer Science 2024-10-24 Clement Neo , Shay B. Cohen , Fazl Barez

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…

Computation and Language · Computer Science 2025-07-17 Yi Zhao , Zuchao Li , Hai Zhao

In human-centered design, developing a comprehensive and in-depth understanding of user experiences, i.e., empathic understanding, is paramount for designing products that truly meet human needs. Nevertheless, accurately comprehending the…

Human-Computer Interaction · Computer Science 2024-03-21 Qihao Zhu , Leah Chong , Maria Yang , Jianxi Luo

Despite excelling on multimodal benchmarks, vision-language models (VLMs) largely remain a black box. In this paper, we propose a novel interpretability framework to systematically analyze the internal mechanisms of VLMs, focusing on the…

Artificial Intelligence · Computer Science 2025-12-12 Yanbei Jiang , Xueqi Ma , Shu Liu , Sarah Monazam Erfani , Tongliang Liu , James Bailey , Jey Han Lau , Krista A. Ehinger

Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to…

Computation and Language · Computer Science 2022-04-07 Shanshan Wang , Zhumin Chen , Zhaochun Ren , Huasheng Liang , Qiang Yan , Pengjie Ren

Large Language Models (LLMs) have been shown to be effective models of the human language system, with some models predicting most explainable variance of brain activity in current datasets. Even in untrained models, the representations…

Computation and Language · Computer Science 2024-06-24 Badr AlKhamissi , Greta Tuckute , Antoine Bosselut , Martin Schrimpf

Recent advances in test-time scaling have enabled Large Language Models (LLMs) to display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation. Despite their potential, these Reasoning LLMs (RLMs) often…

Computation and Language · Computer Science 2025-05-21 Zhen Xiong , Yujun Cai , Zhecheng Li , Yiwei Wang

While large language models (LLMs) demonstrate remarkable success in multilingual translation, their internal core translation mechanisms, even at the fundamental word level, remain insufficiently understood. To address this critical gap,…

Computation and Language · Computer Science 2026-01-16 Hongbin Zhang , Kehai Chen , Xuefeng Bai , Xiucheng Li , Yang Xiang , Min Zhang

Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated…

Computation and Language · Computer Science 2018-08-29 Yujia Bao , Shiyu Chang , Mo Yu , Regina Barzilay

Large language models (LLMs) achieve state-of-the-art performance on multiple language tasks, yet their safety guardrails can be circumvented, leading to harmful generations. In light of this, recent research on safety mechanisms has…

Computation and Language · Computer Science 2025-02-25 Zhenhong Zhou , Haiyang Yu , Xinghua Zhang , Rongwu Xu , Fei Huang , Kun Wang , Yang Liu , Junfeng Fang , Yongbin Li

Large language models (LLMs) have demonstrated human-like abilities in language-based tasks. While language is a defining feature of human intelligence, it emerges from more fundamental neurophysical processes rather than constituting the…

Neurons and Cognition · Quantitative Biology 2025-09-12 Doai Ngo , Mingxuan Sun , Zhengji Zhang , Ashwin G Ramayya , Mark Schnitzer , Zhe Zhao