English
Related papers

Related papers: On Mechanistic Circuits for Extractive Question-An…

200 papers

A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery…

Machine Learning · Computer Science 2025-02-10 Tal Haklay , Hadas Orgad , David Bau , Aaron Mueller , Yonatan Belinkov

Circuit discovery aims to explain how language models (LMs) implement a specific task by localizing and interpreting a circuit, a computational subgraph responsible for the LM's behavior. Existing circuit discovery methods are…

Artificial Intelligence · Computer Science 2026-05-12 Daking Rai , Mor Geva , Ziyu Yao

Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are…

Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable and trustworthy retrieval-augmented generation. We propose a novel framework that formulates…

Artificial Intelligence · Computer Science 2026-04-23 Deng Pan , Keerthiram Murugesan , Ting Hua , Nuno Moniz , Nitesh Chawla

Long-context large language models (LLMs), such as Gemini-2.5-Pro and Claude-Sonnet-4, are increasingly used to empower advanced AI systems, including retrieval-augmented generation (RAG) pipelines and autonomous agents. In these systems,…

Computation and Language · Computer Science 2026-04-21 Yanting Wang , Runpeng Geng , Ying Chen , Jinyuan Jia

Large language models (LLMs) not only exhibit human-like performance but also share computational principles with the brain's language processing mechanisms. While prior research has focused on mapping LLMs' internal representations to…

Computation and Language · Computer Science 2025-04-07 Maryam Rahimi , Yadollah Yaghoobzadeh , Mohammad Reza Daliri

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

Reliance on spurious correlations (shortcuts) has been shown to underlie many of the successes of language models. Previous work focused on identifying the input elements that impact prediction. We investigate how shortcuts are actually…

Machine Learning · Computer Science 2025-05-12 Leon Eshuijs , Shihan Wang , Antske Fokkens

The influence of contextual input on the behavior of large language models (LLMs) has prompted the development of context attribution methods that aim to quantify each context span's effect on an LLM's generations. The leave-one-out (LOO)…

Machine Learning · Computer Science 2025-03-24 Fengyuan Liu , Nikhil Kandpal , Colin Raffel

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

Machine Learning · Computer Science 2026-03-16 Harshwardhan Fartale , Ashish Kattamuri , Rahul Raja , Arpita Vats , Ishita Prasad , Akshata Kishore Moharir

Large language models (LLMs) have emerged as versatile tools in various daily applications. However, they are fraught with issues that undermine their utility and trustworthiness. These include the incorporation of erroneous references…

Computation and Language · Computer Science 2023-09-13 Dongyub Lee , Taesun Whang , Chanhee Lee , Heuiseok Lim

Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as plants or the first word in a sentence. These descriptions are derived using…

Computation and Language · Computer Science 2025-05-30 Yoav Gur-Arieh , Roy Mayan , Chen Agassy , Atticus Geiger , Mor Geva

The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the…

Computation and Language · Computer Science 2024-07-24 Constanza Fierro , Reinald Kim Amplayo , Fantine Huot , Nicola De Cao , Joshua Maynez , Shashi Narayan , Mirella Lapata

In language model interpretability research, \textbf{circuit tracing} aims to identify which internal features causally contributed to a particular output and how they affected each other, with the goal of explaining the computations…

Computation and Language · Computer Science 2026-04-10 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann

Language models can be augmented with a context retriever to incorporate knowledge from large external databases. By leveraging retrieved context, the neural network does not have to memorize the massive amount of world knowledge within its…

Computation and Language · Computer Science 2022-10-13 Zonglin Li , Ruiqi Guo , Sanjiv Kumar

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Computation and Language · Computer Science 2024-12-25 Shuzhang Cai , Twumasi Mensah-Boateng , Xander Kuksov , Jing Yuan , Shaojie Tang

The performance of Large Language Models (LLMs) is significantly sensitive to the contextual position of information in the input. To investigate the mechanism behind this positional bias, our extensive experiments reveal a consistent…

Computation and Language · Computer Science 2025-08-08 Zihao Yi , Delong Zeng , Zhenqing Ling , Haohao Luo , Zhe Xu , Wei Liu , Jian Luan , Wanxia Cao , Ying Shen

Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various…

Computation and Language · Computer Science 2025-06-27 Yongchan Chun , Minhyuk Kim , Dongjun Kim , Chanjun Park , Heuiseok Lim

We introduce EXIT, an extractive context compression framework that enhances both the effectiveness and efficiency of retrieval-augmented generation (RAG) in question answering (QA). Current RAG systems often struggle when retrieval models…

Computation and Language · Computer Science 2025-05-30 Taeho Hwang , Sukmin Cho , Soyeong Jeong , Hoyun Song , SeungYoon Han , Jong C. Park

The study of the attribution of input features to the output of neural network models is an active area of research. While numerous Explainable AI (XAI) techniques have been proposed to interpret these models, the systematic and automated…

Computation and Language · Computer Science 2026-03-13 Aria Nourbakhsh , Salima Lamsiyah , Adelaide Danilov , Christoph Schommer