paper-with-me

홈 › Papers

What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicing

2024-09-14 · Chenyang Yang, Yining Hong, Grace A. Lewis, Tongshuang Wu, Christian Kästner

Machine learning models make mistakes, yet sometimes it is difficult to identify the systematic problems behind the mistakes. Practitioners engage in various activities, including error analysis, testing, auditing, and red-teaming, to form hypotheses of what can go (or has gone) wrong with their models. To validate these hypotheses, practitioners employ data slicing to identify relevant examples. However, traditional data slicing is limited by available features and programmatic slicing functions. In this work, we propose SemSlicer, a framework that supports semantic data slicing, which identifies a semantically coherent slice, without the need for existing features. SemSlicer uses Large Language Models to annotate datasets and generate slices from any user-defined slicing criteria. We show that SemSlicer generates accurate slices with low cost, allows flexible trade-offs between different design dimensions, reliably identifies under-performing data slices, and helps practitioners identify useful data slices that reflect systematic problems.

📄 PDF Abstract BibTeX arXiv:2409.09261

Code (1)

malusamayo/SemSlicer 공식 구현 pytorch

Tasks

Red Teaming

Similar Papers 제목 키워드 기반

Prediction of Video Game Development Problems Based on Postmortems using Different Word Embedding Techniques

2021-12-01 · ICON 2021 12 · Anirudh A, Aman RAJ Singh, Anjali Goyal, Lov Kumar 외

The interactive entertainment industry is being actively involved with the development, marketing and sale of video games in the past decade. The increasing interest in video games has led to an increase in video game de…

Marketing

Murphys Laws of AI Alignment: Why the Gap Always Wins

2025-09-04 · Madhava Gaikwad arxiv

We study reinforcement learning from human feedback under misspecification. Sometimes human feedback is systematically wrong on certain types of inputs, like a broken compass that points the wrong way in specific regions…

Reinforcement Learning

Controlled abstention neural networks for identifying skillful predictions for classification problems

2021-04-16 · Elizabeth A. Barnes, Randal J. Barnes

The earth system is exceedingly complex and often chaotic in nature, making prediction incredibly challenging: we cannot expect to make perfect predictions all of the time. Instead, we look for specific states of the sys…

General Classification

Confident and Wrong: Silent Semantic Failures in Coding Agents

2026-03-26 · Aman Mehta arxiv

As coding agents move into production workflows, teams need to know not only whether an agent completes a task, but whether its action can be trusted. We show that completion and trustworthiness diverge sharply and syste…

Style over Substance: Distilled Language Models Reason Via Stylistic Replication

2025-04-02 · Philip Lippmann, Jie Yang

Specialized reasoning language models (RLMs) have demonstrated that scaling test-time computation through detailed reasoning traces significantly enhances performance. Although these traces effectively facilitate knowled…

Knowledge Distillation