English
Related papers

Related papers: Fixing Model Bugs with Natural Language Patches

200 papers

We formulate the novel task of automatically updating an existing natural language comment based on changes in the body of code it accompanies. We propose an approach that learns to correlate changes across two distinct language…

Computation and Language · Computer Science 2020-04-29 Sheena Panthaplackel , Pengyu Nie , Milos Gligoric , Junyi Jessy Li , Raymond J. Mooney

Large language models (LLMs), such as OpenAI's Codex, have demonstrated their potential to generate code from natural language descriptions across a wide range of programming tasks. Several benchmarks have recently emerged to evaluate the…

Software Engineering · Computer Science 2023-04-11 Sarah Fakhoury , Saikat Chakraborty , Madan Musuvathi , Shuvendu K. Lahiri

Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and in turn small…

Computation and Language · Computer Science 2023-03-08 Peyman Jalali , Nengfeng Zhou , Yufei Yu

Timely and effective vulnerability patching is essential for cybersecurity defense, for which various approaches have been proposed yet still struggle to generate valid and correct patches for real-world vulnerabilities. In this paper, we…

Cryptography and Security · Computer Science 2025-04-04 Yu Nong , Haoran Yang , Long Cheng , Hongxin Hu , Haipeng Cai

Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these…

Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors. This work explores whether…

Computation and Language · Computer Science 2024-06-07 Yunxiang Zhang , Muhammad Khalifa , Lajanugen Logeswaran , Jaekyeom Kim , Moontae Lee , Honglak Lee , Lu Wang

Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are…

Computation and Language · Computer Science 2023-07-03 Pepa Atanasova , Oana-Maria Camburu , Christina Lioma , Thomas Lukasiewicz , Jakob Grue Simonsen , Isabelle Augenstein

Automated Program Repair (APR) can help developers automatically generate patches for bugs. Due to the impressive performance obtained using Large Pre-Trained Language Models (LLMs) on many code related tasks, researchers have started to…

Software Engineering · Computer Science 2023-02-01 Chunqiu Steven Xia , Lingming Zhang

Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and…

Computation and Language · Computer Science 2024-02-20 Rajan Vivek , Kawin Ethayarajh , Diyi Yang , Douwe Kiela

Natural Language Inference (NLI) models have been used in various ways to improve the factuality of LLM outputs. This is typically done by applying an NLI model to judge whether the model output is entailed from the supposed evidence,…

Computation and Language · Computer Science 2025-11-04 Sapir Harary , Eran Hirsch , Aviv Slobodkin , David Wan , Mohit Bansal , Ido Dagan

Recent research has shown that incorporating bug-related facts, such as stack traces and GitHub issues, into prompts enhances the bug-fixing capabilities of large language models (LLMs). Considering the ever-increasing context window of…

Software Engineering · Computer Science 2024-08-28 Nikhil Parasaram , Huijie Yan , Boyu Yang , Zineb Flahy , Abriele Qudsi , Damian Ziaber , Earl Barr , Sergey Mechtaev

Automatically fixing software bugs is a challenging task. While recent work showed that natural language context is useful in guiding bug-fixing models, the approach required prompting developers to provide this context, which was simulated…

Software Engineering · Computer Science 2022-11-14 Sheena Panthaplackel , Milos Gligoric , Junyi Jessy Li , Raymond J. Mooney

Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however, currently trained with a large amount of…

Computation and Language · Computer Science 2022-04-27 Ana Marasović , Iz Beltagy , Doug Downey , Matthew E. Peters

Natural language correction has the potential to help language learners improve their writing skills. While approaches with separate classifiers for different error types have high precision, they do not flexibly handle errors such as…

Computation and Language · Computer Science 2016-04-01 Ziang Xie , Anand Avati , Naveen Arivazhagan , Dan Jurafsky , Andrew Y. Ng

Lack of repeatability and generalisability are two significant threats to continuing scientific development in Natural Language Processing. Language models and learning methods are so complex that scientific conference papers no longer…

Computation and Language · Computer Science 2018-08-07 Andrew Moore , Paul Rayson

Bugs are notoriously challenging: they slow down software users and result in time-consuming investigations for developers. These challenges are exacerbated when bugs must be reported in natural language by users. Indeed, we lack reliable…

Software Engineering · Computer Science 2023-10-11 Laura Plein , Tegawendé F. Bissyandé

Evaluation practices in natural language generation (NLG) have many known flaws, but improved evaluation approaches are rarely widely adopted. This issue has become more urgent, since neural NLG models have improved to the point where they…

Computation and Language · Computer Science 2022-02-15 Sebastian Gehrmann , Elizabeth Clark , Thibault Sellam

Localizing behaviors of neural networks to a subset of the network's components or a subset of interactions between components is a natural first step towards analyzing network mechanisms and possible failure modes. Existing work is often…

Machine Learning · Computer Science 2023-05-17 Nicholas Goldowsky-Dill , Chris MacLeod , Lucas Sato , Aryaman Arora

While language models demonstrate sophisticated syntactic capabilities, the extent to which their internal mechanisms align with cross-constructional principles studied in linguistics remains poorly understood. This study investigates…

Computation and Language · Computer Science 2026-04-27 Ryoma Kumon , Hitomi Yanaka

Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity with the process of human learning makes learning from…

Computation and Language · Computer Science 2022-04-20 Mareike Hartmann , Daniel Sonntag