English
Related papers

Related papers: Discover, Explanation, Improvement: An Automatic S…

200 papers

Recent large language models (LLMs) have demonstrated the ability to perform explicit multi-step reasoning such as chain-of-thought prompting. However, their intermediate steps often contain errors that can propagate leading to inaccurate…

Artificial Intelligence · Computer Science 2025-08-06 Yijin Yang , Cristina Cornelio , Mario Leiva , Paulo Shakarian

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

Computation and Language · Computer Science 2025-03-21 Ishika Agarwal , Krishnateja Killamsetty , Lucian Popa , Marina Danilevksy

Error slice discovery is crucial to diagnose and mitigate model errors. Current clustering or discrete attribute-based slice discovery methods face key limitations: 1) clustering results in incoherent slices, while assigning discrete…

Computation and Language · Computer Science 2025-06-02 Shantanu Ghosh , Rayan Syed , Chenyu Wang , Vaibhav Choudhary , Binxu Li , Clare B. Poynton , Shyam Visweswaran , Kayhan Batmanghelich

Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets ("slices") of data. This behavior can have significant societal consequences for the safety or bias of the model in…

Human-Computer Interaction · Computer Science 2024-02-12 Nari Johnson , Ángel Alexander Cabrera , Gregory Plumb , Ameet Talwalkar

Large Language Models (LLMs) often exhibit systematic errors on specific subsets of data, known as error slices. For instance, a slice can correspond to a certain demographic, where a model does poorly in identifying toxic comments…

Machine Learning · Computer Science 2025-11-27 Minhui Zhang , Prahar Ijner , Yoav Wald , Elliot Creager

Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the root causes of their failures is critical for model…

Machine Learning · Computer Science 2026-05-29 Yael Konforti , Mateo Espinosa Zarlenga , Elaf Almahmoud , Mateja Jamnik

Machine learning models have achieved high overall accuracy in medical image analysis. However, performance disparities on specific patient groups pose challenges to their clinical utility, safety, and fairness. This can affect known…

Machine Learning · Computer Science 2024-10-23 Vincent Olesen , Nina Weng , Aasa Feragen , Eike Petersen

Recent work has made a preliminary attempt to use large language models (LLMs) to solve the stance detection task, showing promising results. However, considering that stance detection usually requires detailed background knowledge, the…

Computation and Language · Computer Science 2024-04-29 Xiaolong Wang , Yile Wang , Sijie Cheng , Peng Li , Yang Liu

Slice discovery methods (SDMs) are prominent algorithms for finding systematic weaknesses in DNNs. They identify top-k semantically coherent slices/subsets of data where a DNN-under-test has low performance. For being directly useful,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Sujan Sai Gannamaneni , Rohil Prakash Rao , Michael Mock , Maram Akila , Stefan Wrobel

In real-world machine learning applications, data subsets correspond to especially critical outcomes: vulnerable cyclist detections are safety-critical in an autonomous driving task, and "question" sentences might be important to a dialogue…

Machine Learning · Computer Science 2020-03-03 Vincent S. Chen , Sen Wu , Zhenzhen Weng , Alexander Ratner , Christopher Ré

Semantic Textual Similarity (STS) is a crucial component of many Natural Language Processing (NLP) applications. However, existing approaches typically reduce semantic nuances to a single score, limiting interpretability. To address this,…

Computation and Language · Computer Science 2026-05-15 Diego Miguel Lozano , Daryna Dementieva , Alexander Fraser

Systematic failures of computer vision models on subsets with coherent visual patterns, known as error slices, pose a critical challenge for robust model evaluation. Existing slice discovery methods are primarily developed for image…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Wei Zhang , Chaoqun Wang , Zixuan Guan , Sam Kao , Pengfei Zhao , Peng Wu , Sifeng He

Large Language Models (LLMs) have demonstrated substantial capabilities in conversational AI applications, yet their susceptibility to dialogue breakdowns poses significant challenges to deployment reliability and user trust. This paper…

Computation and Language · Computer Science 2026-01-12 Abdellah Ghassel , Xianzhi Li , Xiaodan Zhu

Based on official estimates, 50 million people worldwide are affected by dementia, and this number increases by 10 million new patients every year. Without a cure, clinical prognostication and early intervention represent the most effective…

Computation and Language · Computer Science 2024-09-06 Francisco de Arriba-Pérez , Silvia García-Méndez

Dataset pruning aims to select a subset of a dataset for efficient model training. While data efficiency in natural language processing has primarily focused on within-corpus scenarios during model pre-training, efficient dataset pruning…

Computation and Language · Computer Science 2025-01-07 Binh-Nguyen Nguyen , Yang He

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their…

Machine Learning · Computer Science 2026-05-06 Jinbin Bai , Yixuan Li , Yuchen Zhu , Yi Xin , Qingyu Shi , Aosong Feng , Xiaohong Liu , Molei Tao , Jianru Xue , Xiangtai Li , Ming-Hsuan Yang

When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to…

Computation and Language · Computer Science 2025-10-21 Yiqi Li , Yusheng Liao , Zhe Chen , Yanfeng Wang , Yu Wang

The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets often comprise valuable instruction-response pairs, making…

Cryptography and Security · Computer Science 2025-06-24 Zongjie Li , Daoyuan Wu , Shuai Wang , Zhendong Su

Decompilers are important tools for reverse engineers that help them analyze software at a higher level of abstraction than assembly code. Unfortunately, because compilation is lossy, deterministic decompilers produce code that is missing…

Software Engineering · Computer Science 2025-06-18 Luke Dramko , Claire Le Goues , Edward J. Schwartz

Novelty detection in discrete sequences is a challenging task, since deviations from the process generating the normal data are often small or intentionally hidden. Novelties can be detected by modeling normal sequences and measuring the…

Machine Learning · Computer Science 2023-07-11 Linara Adilova , Siming Chen , Michael Kamp
‹ Prev 1 2 3 10 Next ›