English
Related papers

Related papers: Localized Definitions and Distributed Reasoning: A…

200 papers

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Computation and Language · Computer Science 2026-03-12 Ajay Pravin Mahale

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

Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model's reasoning on an objective task. Using activation patching, we take a first step…

Machine Learning · Computer Science 2025-09-23 Ansh Poonia , Maeghal Jain

Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. However, the faithfulness of these explanations should not be readily trusted at face value. Recent studies…

Computation and Language · Computer Science 2024-11-04 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

We study how large language models recall relational knowledge during text generation, with a focus on identifying latent representations suitable for relation classification via linear probes. Prior work shows how attention heads and MLPs…

Computation and Language · Computer Science 2026-04-24 Nicholas Popovič , Michael Färber

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze…

Machine Learning · Computer Science 2024-02-20 Leon Sixt , Maximilian Granz , Tim Landgraf

Computational methods to aid journalists in the task often require adapting a model to specific domains and generating explanations. However, most automated fact-checking methods rely on three-class datasets, which do not accurately reflect…

Computation and Language · Computer Science 2024-10-08 Jing Yang , Anderson Rocha

Language models learn a great quantity of factual information during pretraining, and recent work localizes this information to specific model weights like mid-layer MLP weights. In this paper, we find that we can change how a fact is…

Machine Learning · Computer Science 2023-10-17 Peter Hase , Mohit Bansal , Been Kim , Asma Ghandeharioun

Current approaches for fixing systematic problems in NLP models (e.g. regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide corrections to each other…

Computation and Language · Computer Science 2022-11-22 Shikhar Murty , Christopher D. Manning , Scott Lundberg , Marco Tulio Ribeiro

Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models. Existing automated circuit discovery work applies activation…

Machine Learning · Computer Science 2023-11-21 Aaquib Syed , Can Rager , Arthur Conmy

Knowledge stored in large language models requires timely updates to reflect the dynamic nature of real-world information. To update the knowledge, most knowledge editing methods focus on the low layers, since recent probes into the…

Computation and Language · Computer Science 2024-12-25 Wenhang Shi , Yiren Chen , Shuqing Bian , Xinyi Zhang , Zhe Zhao , Pengfei Hu , Wei Lu , Xiaoyong Du

This reproducibility study analyzes and extends the paper "Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models," which investigates how neural retrieval models encode task-relevant…

Information Retrieval · Computer Science 2025-05-06 Oliver Savolainen , Dur e Najaf Amjad , Roxana Petcu

Interpretability remains a key difficulty in sentiment analysis with Large Language Models (LLMs), particularly in high-stakes applications where it is crucial to comprehend the rationale behind forecasts. This research addressed this by…

Computation and Language · Computer Science 2025-03-18 Thivya Thogesan , Anupiya Nugaliyadde , Kok Wai Wong

Deep convolutional neural networks (CNN) always depend on wider receptive field (RF) and more complex non-linearity to achieve state-of-the-art performance, while suffering the increased difficult to interpret how relevant patches…

Computer Vision and Pattern Recognition · Computer Science 2020-04-20 Chuanguang Yang , Zhulin An , Xiaolong Hu , Hui Zhu , Yongjun Xu

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

Computation and Language · Computer Science 2026-03-17 Yu Liu , Wenxiao Zhang , Diandian Guo , Cong Cao , Fangfang Yuan , Qiang Sun , Yanbing Liu , Jin B. Hong , Zhiyuan Ma

In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary…

Machine Learning · Computer Science 2019-01-17 Sebastian Kauschke , David Hermann Lehmann

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

Computation and Language · Computer Science 2025-07-16 Pedro Ferreira , Wilker Aziz , Ivan Titov

Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explainability method. However, recent research has exposed the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Thomas Fel , Agustin Picard , Louis Bethune , Thibaut Boissin , David Vigouroux , Julien Colin , Rémi Cadène , Thomas Serre

Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual information. Yet they are trained on static corpora and may encode incorrect facts. Existing…

Machine Learning · Computer Science 2026-03-17 Sung Kyun Chung , Jiaheng Dong , Qiuchi Hu , Gongping Huang , Hong Jia , Ting Dang

Explaining machine learning (ML) predictions has become crucial as ML models are increasingly deployed in high-stakes domains such as healthcare. While SHapley Additive exPlanations (SHAP) is widely used for model interpretability, it fails…

Machine Learning · Computer Science 2025-09-03 Woon Yee Ng , Li Rong Wang , Siyuan Liu , Xiuyi Fan