English
Related papers

Related papers: Fine-Grained Analysis of Shared Syntactic Mechanis…

200 papers

Mechanistic interpretability seeks to understand the internal mechanisms of machine learning models, where localization -- identifying the important model components -- is a key step. Activation patching, also known as causal tracing or…

Machine Learning · Computer Science 2024-01-18 Fred Zhang , Neel Nanda

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept…

Computation and Language · Computer Science 2026-02-02 Felicia Körner , Max Müller-Eberstein , Anna Korhonen , Barbara Plank

Brain-to-speech decoding models demonstrate robust performance in vocalized, mimed, and imagined speech; yet, the fundamental mechanisms via which these models capture and transmit information across different speech modalities are less…

Machine Learning · Computer Science 2026-02-03 Maryam Maghsoudi , Ayushi Mishra

Language Models (LMs) have emerged as powerful sources of evidence for linguists seeking to develop theories of syntax. In this paper, we argue that causal interpretability methods, applied to LMs, can greatly enhance the value of such…

Computation and Language · Computer Science 2025-10-01 Sasha Boguraev , Christopher Potts , Kyle Mahowald

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

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

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

This study investigates the localization of knowledge representation in fine-tuned GPT-2 models using Causal Layer Attribution via Activation Patching (CLAP), a method that identifies critical neural layers responsible for correct answer…

Machine Learning · Computer Science 2025-04-07 Nooshin Bahador

Structural probing work has found evidence for latent syntactic information in pre-trained language models. However, much of this analysis has focused on monolingual models, and analyses of multilingual models have employed correlational…

Computation and Language · Computer Science 2022-10-27 Aaron Mueller , Yu Xia , Tal Linzen

Targeted syntactic evaluations have demonstrated the ability of language models to perform subject-verb agreement given difficult contexts. To elucidate the mechanisms by which the models accomplish this behavior, this study applies causal…

Computation and Language · Computer Science 2021-06-23 Matthew Finlayson , Aaron Mueller , Sebastian Gehrmann , Stuart Shieber , Tal Linzen , Yonatan Belinkov

A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be composed to perform more complex tasks. Recent advances in…

Machine Learning · Computer Science 2025-06-24 Philipp Mondorf , Sondre Wold , Barbara Plank

Deep compositional models of meaning acting on distributional representations of words in order to produce vectors of larger text constituents are evolving to a popular area of NLP research. We detail a compositional distributional…

Computation and Language · Computer Science 2015-08-14 Jianpeng Cheng , Dimitri Kartsaklis

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of familiar words and…

Computation and Language · Computer Science 2021-11-10 Wang Zhu , Peter Shaw , Tal Linzen , Fei Sha

For humans, filler-gap dependencies require a shared representation across different syntactic constructions. Although causal analyses suggest this may also be true for LLMs (Boguraev et al., 2025), it is still unclear if such a…

Computation and Language · Computer Science 2026-04-17 Atrey Desai , Sathvik Nair

Mechanistic interpretability (MI) seeks to uncover how language models (LMs) implement specific behaviors, yet measuring progress in MI remains challenging. The recently released Mechanistic Interpretability Benchmark (MIB; Mueller et al.,…

Computation and Language · Computer Science 2025-11-25 Dana Arad , Yonatan Belinkov , Hanjie Chen , Najoung Kim , Hosein Mohebbi , Aaron Mueller , Gabriele Sarti , Martin Tutek

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

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy…

Computation and Language · Computer Science 2023-08-29 Vedant Palit , Rohan Pandey , Aryaman Arora , Paul Pu Liang

In this paper, we propose to study language modelling as a multi-task problem, bringing together three strands of research: multi-task learning, linguistics, and interpretability. Based on hypotheses derived from linguistic theory, we…

Computation and Language · Computer Science 2021-01-28 Lucas Weber , Jaap Jumelet , Elia Bruni , Dieuwke Hupkes

Mechanistic interpretability seeks to localize model behavior to the internal components that causally realize it. Prior work has advanced activation-space localization and causal tracing, but modules that appear important in activation…

Artificial Intelligence · Computer Science 2026-04-16 Chenghao Sun , Chengsheng Zhang , Guanzheng Qin , Rui Dai , Xinmei Tian

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann
‹ Prev 1 2 3 10 Next ›