English
Related papers

Related papers: Enhancing Automated Interpretability with Output-C…

200 papers

Word representations induced from models with discrete latent variables (e.g.\ HMMs) have been shown to be beneficial in many NLP applications. In this work, we exploit labeled syntactic dependency trees and formalize the induction problem…

Computation and Language · Computer Science 2016-02-08 Simon Šuster , Gertjan van Noord , Ivan Titov

As machine learning becomes increasingly integral to autonomous decision-making processes involving human interaction, the necessity of comprehending the model's outputs through conversational means increases. Most recently, foundation…

Artificial Intelligence · Computer Science 2024-07-31 Sule Tekkesinoglu , Lars Kunze

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…

Computation and Language · Computer Science 2025-11-11 Giuseppe Birardi

Prompt Engineering has garnered significant attention for enhancing the performance of large language models across a multitude of tasks. Techniques such as the Chain-of-Thought not only bolster task performance but also delineate a clear…

Computation and Language · Computer Science 2024-10-21 Wei Jie Yeo , Ranjan Satapathy , Rick Siow Mong Goh , Erik Cambria

We investigate whether large language models (LLMs) can generate effective, user-facing explanations from a mathematically interpretable recommendation model. The model is based on constrained matrix factorization, where user types are…

Artificial Intelligence · Computer Science 2025-10-02 Maxime Manderlier , Fabian Lecron , Olivier Vu Thanh , Nicolas Gillis

The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding model computations. Existing approaches, however, rely on…

Machine Learning · Computer Science 2026-03-05 Elena Golimblevskaia , Aakriti Jain , Bruno Puri , Ammar Ibrahim , Wojciech Samek , Sebastian Lapuschkin

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Computation and Language · Computer Science 2026-05-05 Or Shafran , Atticus Geiger , Mor Geva

Automated machine learning (AutoML) systems aim to enable training machine learning (ML) models for non-ML experts. A shortcoming of these systems is that when they fail to produce a model with high accuracy, the user has no path to improve…

Machine Learning · Computer Science 2021-02-23 Behnaz Arzani , Kevin Hsieh , Haoxian Chen

Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain poorly understood. In this work, we present a mechanistic…

Computation and Language · Computer Science 2026-04-02 Miranda Muqing Miao , Lyle Ungar

Large language models (LLMs) show promising capabilities in predicting human emotions from text. However, the mechanisms through which these models process emotional stimuli remain largely unexplored. Our study addresses this gap by…

Computation and Language · Computer Science 2025-07-01 Ala N. Tak , Amin Banayeeanzade , Anahita Bolourani , Mina Kian , Robin Jia , Jonathan Gratch

Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable…

The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problems (e.g., cloze tests) is a natural approach for…

Computation and Language · Computer Science 2020-11-10 Taylor Shin , Yasaman Razeghi , Robert L. Logan , Eric Wallace , Sameer Singh

Large language models (LLMs) such as ChatGPT have demonstrated superior performance on a variety of natural language processing (NLP) tasks including sentiment analysis, mathematical reasoning and summarization. Furthermore, since these…

Computation and Language · Computer Science 2023-10-18 Shiyuan Huang , Siddarth Mamidanna , Shreedhar Jangam , Yilun Zhou , Leilani H. Gilpin

Feature importance estimates that inform users about the degree to which given inputs influence the output of a predictive model are crucial for understanding, validating, and interpreting machine-learning models. However, providing fast…

Machine Learning · Computer Science 2019-10-29 Patrick Schwab , Walter Karlen

Phrases are fundamental linguistic units through which humans convey semantics. This study critically examines the capacity of API-based large language models (LLMs) to comprehend phrase semantics, utilizing three human-annotated datasets.…

Computation and Language · Computer Science 2024-10-04 Rui Meng , Ye Liu , Lifu Tu , Daqing He , Yingbo Zhou , Semih Yavuz

Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given…

Machine Learning · Computer Science 2026-03-05 Takashi Kameyama , Masahiro Kato , Yasuko Hio , Yasushi Takano , Naoto Minakawa

We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features for linear models. CHiLL prompts LLMs with expert-crafted queries to generate interpretable features from health records. The…

Computation and Language · Computer Science 2023-10-23 Denis Jered McInerney , Geoffrey Young , Jan-Willem van de Meent , Byron C. Wallace

Large Language Models (LLMs) are reported to hold undesirable attestation bias on inference tasks: when asked to predict if a premise P entails a hypothesis H, instead of considering H's conditional truthfulness entailed by P, LLMs tend to…

Computation and Language · Computer Science 2024-08-27 Tianyang Liu , Tianyi Li , Liang Cheng , Mark Steedman

Several explainable AI methods allow a Machine Learning user to get insights on the classification process of a black-box model in the form of local linear explanations. With such information, the user can judge which features are locally…

Machine Learning · Computer Science 2023-02-16 Francesco Lomuscio , Paolo Bajardi , Alan Perotti , Elvio G. Amparore

Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature…

Machine Learning · Statistics 2019-10-09 Amirata Ghorbani , James Wexler , James Zou , Been Kim