English
Related papers

Related papers: Does Localization Inform Editing? Surprising Diffe…

200 papers

The success of large language models (LLMs) can be attributed in part to their ability to efficiently store factual knowledge as key-value mappings within their MLP parameters. Recent work has proposed explicit weight constructions to build…

Machine Learning · Computer Science 2025-12-02 Owen Dugan , Roberto Garcia , Ronny Junkins , Jerry Liu , Dylan Zinsley , Sabri Eyuboglu , Atri Rudra , Chris Ré

Knowledge editing aims to modify outdated knowledge in language models efficiently while retaining their original capabilities. Mainstream datasets for knowledge editing are predominantly static and fail to keep in pace with the evolving…

Computation and Language · Computer Science 2026-04-24 Chenming Tang , Yutong Yang , Kexue Wang , Yunfang Wu

When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Chih-Yao Ma , Yannis Kalantidis , Ghassan AlRegib , Peter Vajda , Marcus Rohrbach , Zsolt Kira

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

Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution. Recently, several proposed debiasing methods are…

Computation and Language · Computer Science 2020-05-04 Prasetya Ajie Utama , Nafise Sadat Moosavi , Iryna Gurevych

Model editing has recently emerged as a popular paradigm for efficiently updating knowledge in LLMs. A central desideratum of updating knowledge is to balance editing efficacy, i.e., the successful injection of target knowledge, and…

Artificial Intelligence · Computer Science 2026-01-27 Wei Liu , Haomei Xu , Hongkai Liu , Zhiying Deng , Ruixuan Li , Heng Huang , Yee Whye Teh , Wee Sun Lee

Recently, Locate-Then-Edit paradigm has emerged as one of the main approaches in changing factual knowledge stored in the Language models. However, there is a lack of research on whether present locating methods can pinpoint the exact…

Computation and Language · Computer Science 2024-08-27 Yiming Ju , Xingrun Xing , Zhixiong Zeng

Knowledge editing has emerged as a lightweight alternative to retraining for correcting or injecting specific facts in large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and…

Computation and Language · Computer Science 2025-12-09 Yinjie Cheng , Paul Youssef , Christin Seifert , Jörg Schlötterer , Zhixue Zhao

Interpretability research aims to bridge the gap between empirical success and our scientific understanding of the inner workings of large language models (LLMs). However, most existing research focuses on analyzing a single mechanism, such…

Computation and Language · Computer Science 2024-06-10 Francesco Ortu , Zhijing Jin , Diego Doimo , Mrinmaya Sachan , Alberto Cazzaniga , Bernhard Schölkopf

Large Transformer models have achieved impressive performance in many natural language tasks. In particular, Transformer based language models have been shown to have great capabilities in encoding factual knowledge in their vast amount of…

Computation and Language · Computer Science 2020-12-02 Chen Zhu , Ankit Singh Rawat , Manzil Zaheer , Srinadh Bhojanapalli , Daliang Li , Felix Yu , Sanjiv Kumar

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

Knowledge editing aims to efficiently correct factual errors in language models. Widely used locate-then-edit methods update an MLP layer by adjusting its weights to change the mapping between the layer's input vector (key) and output…

Computation and Language · Computer Science 2026-03-03 Haewon Park , Sangwoo Kim , Yohan Jo

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Computation and Language · Computer Science 2021-09-10 Michael Mendelson , Yonatan Belinkov

Recent work on reducing bias in NLP models usually focuses on protecting or isolating information related to a sensitive attribute (like gender or race). However, when sensitive information is semantically entangled with the task…

Computation and Language · Computer Science 2022-10-25 Zexue He , Yu Wang , Julian McAuley , Bodhisattwa Prasad Majumder

Causal modeling has been recognized as a potential solution to many challenging problems in machine learning (ML). Here, we describe how a recently proposed counterfactual approach developed to deconfound linear structural causal models can…

Machine Learning · Computer Science 2020-11-23 Elias Chaibub Neto

This paper investigates models of event implications. Specifically, how well models predict entity state-changes, by targeting their understanding of physical attributes. Nominally, Large Language models (LLM) have been exposed to…

Computation and Language · Computer Science 2022-11-11 Evangelia Spiliopoulou , Artidoro Pagnoni , Yonatan Bisk , Eduard Hovy

Model editing is a technique that edits the large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining. While current model editing methods can effectively modify a model's behavior…

Computation and Language · Computer Science 2024-10-08 Jia-Chen Gu , Hao-Xiang Xu , Jun-Yu Ma , Pan Lu , Zhen-Hua Ling , Kai-Wei Chang , Nanyun Peng

Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations…

Computation and Language · Computer Science 2024-03-12 Yung-Sung Chuang , Yujia Xie , Hongyin Luo , Yoon Kim , James Glass , Pengcheng He

Multiple studies have probed representations emerging in neural networks trained for end-to-end NLP tasks and examined what word-level linguistic information may be encoded in the representations. In classical probing, a classifier is…

Computation and Language · Computer Science 2021-10-26 Rudolf Rosa , Tomáš Musil , David Mareček

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

Computation and Language · Computer Science 2021-12-13 Lei Ding , Dengdeng Yu , Jinhan Xie , Wenxing Guo , Shenggang Hu , Meichen Liu , Linglong Kong , Hongsheng Dai , Yanchun Bao , Bei Jiang