English
Related papers

Related papers: Copy Suppression: Comprehensively Understanding an…

200 papers

Prior interpretability research studying narrow distributions has preliminarily identified self-repair, a phenomena where if components in large language models are ablated, later components will change their behavior to compensate. Our…

Machine Learning · Computer Science 2025-04-15 Cody Rushing , Neel Nanda

We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers. At the end of training, the model organizes its attention heads in two main modes that we refer to as…

Machine Learning · Computer Science 2025-02-03 Einar Urdshals , Jasmina Urdshals

Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does CoT contribute if not logical sequencing? In three 1-3B instruction-tuned LMs on GSM8K, we…

Machine Learning · Computer Science 2026-05-25 Ming Liu

Negation remains a persistent challenge for modern language models, often causing reversed meanings or factual errors. In this work, we conduct a causal analysis of how GPT-2 Small internally processes such linguistic transformations. We…

Computation and Language · Computer Science 2026-03-16 Abdullah Al Mofael , Lisa M. Kuhn , Ghassan Alkadi , Kuo-Pao Yang

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

Two of the central factors believed to underpin human sentence processing difficulty are expectations and retrieval from working memory. A recent attempt to create a unified cognitive model integrating these two factors relied on the…

Computation and Language · Computer Science 2023-10-26 William Timkey , Tal Linzen

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

Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…

Computation and Language · Computer Science 2025-05-26 Anurag Mishra

This paper investigates the role of attention heads in CLIP's image encoder. Building on interpretability studies, we conduct an exhaustive analysis and find that certain heads, distributed across layers, are detrimental to the resulting…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Feng Lin , Marco Chen , Haokui Zhang , Xiaotian Yu , Guangming Lu , Rong Xiao

Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrinsic complexity, these models present substantial challenges…

Machine Learning · Computer Science 2024-10-17 Ashkan Golgoon , Khashayar Filom , Arjun Ravi Kannan

Induction heads are attention heads that perform inductive copying by matching patterns from earlier context and copying their continuations verbatim. As models develop induction heads, they experience a sharp drop in training loss, a…

Computation and Language · Computer Science 2026-02-11 Kerem Sahin , Sheridan Feucht , Adam Belfki , Jannik Brinkmann , Aaron Mueller , David Bau , Chris Wendler

Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information loss during decoding, creating critical challenges for KV cache compression. Existing…

Computation and Language · Computer Science 2026-05-28 Wenjie Du , Li Jiang , Keda Tao , Xue Liu , Huan Wang

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia

Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, but their role in diffusion transformers remains unclear. We present a causal analysis in…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Fangzheng Wu , Brian Summa

Large language models (LLMs) have demonstrated impressive few-shot in-context learning (ICL) abilities. Still, we show that they are sometimes prone to a `copying bias', where they copy answers from provided examples instead of learning the…

Computation and Language · Computer Science 2024-10-04 Ameen Ali , Lior Wolf , Ivan Titov

A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of their decisions on specific issues. In this work, we observe…

Computation and Language · Computer Science 2025-04-30 Sangwon Yu , Jongyoon Song , Bongkyu Hwang , Hoyoung Kang , Sooah Cho , Junhwa Choi , Seongho Joe , Taehee Lee , Youngjune L. Gwon , Sungroh Yoon

Previous studies have shown that initializing neural machine translation (NMT) models with the pre-trained language models (LM) can speed up the model training and boost the model performance. In this work, we identify a critical…

Computation and Language · Computer Science 2021-07-20 Xuebo Liu , Longyue Wang , Derek F. Wong , Liang Ding , Lidia S. Chao , Shuming Shi , Zhaopeng Tu

The neural attention mechanism plays an important role in many natural language processing applications. In particular, the use of multi-head attention extends single-head attention by allowing a model to jointly attend information from…

Machine Learning · Computer Science 2020-11-03 Bang An , Jie Lyu , Zhenyi Wang , Chunyuan Li , Changwei Hu , Fei Tan , Ruiyi Zhang , Yifan Hu , Changyou Chen

Large language models (LLMs) have shown a remarkable ability to learn and perform complex tasks through in-context learning (ICL). However, a comprehensive understanding of its internal mechanisms is still lacking. This paper explores the…

Computation and Language · Computer Science 2025-04-03 Joy Crosbie , Ekaterina Shutova
‹ Prev 1 2 3 10 Next ›