paper-with-me

홈 › Papers

On the Relation between Sensitivity and Accuracy in In-context Learning

2022-09-16 · Yanda Chen, Chen Zhao, Zhou Yu, Kathleen McKeown, He He

In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios. We study the sensitivity of ICL with respect to multiple perturbation types. First, we find that label bias obscures the true sensitivity, and therefore prior work may have significantly underestimated ICL sensitivity. Second, we observe a strong negative correlation between ICL sensitivity and accuracy: predictions sensitive to perturbations are less likely to be correct. Motivated by these findings, we propose \textsc{SenSel}, a few-shot selective prediction method that abstains from sensitive predictions. Experiments on ten classification datasets show that \textsc{SenSel} consistently outperforms two commonly used confidence-based and entropy-based baselines on abstention decisions.

📄 PDF Abstract BibTeX arXiv:2209.07661

Code (1)

yandachen/iclsensitivity 공식 구현 pytorch

Tasks

In-Context LearningRelationSensitivity

Similar Papers 제목 키워드 기반

Controllable Context Sensitivity and the Knob Behind It

2024-11-11 · Julian Minder, Kevin Du, Niklas Stoehr, Giovanni Monea 외

When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamental functionality, as it enables the mod…

Question AnsweringRetrieval-augmented GenerationSensitivity

Between Rules and Reality: On the Context Sensitivity of LLM Moral Judgment

2026-03-24 · Adrian Sauter, Mona Schirmer arxiv

A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We address this gap by introducing Contextual MoralChoice, a dataset of moral dilemmas with syste…

Gradient-based Active Learning with Gaussian Processes for Global Sensitivity Analysis

2026-01-16 · Guerlain Lambert, Céline Helbert, Claire Lauvernet arxiv

Global sensitivity analysis of complex numerical simulators is often limited by the small number of model evaluations that can be afforded. In such settings, surrogate models built from a limited set of simulations can s…

Gaussian ProcessesActive Learning

How are Prompts Different in Terms of Sensitivity?

2023-11-13 · Sheng Lu, Hendrik Schuff, Iryna Gurevych

In-context learning (ICL) has become one of the most popular learning paradigms. While there is a growing body of literature focusing on prompt engineering, there is a lack of systematic analysis comparing the effects of…

In-Context LearningPrompt EngineeringSensitivity

Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships

2023-07-06 · David Jurgens, Agrima Seth, Jackson Sargent, Athena Aghighi 외

Understanding interpersonal communication requires, in part, understanding the social context and norms in which a message is said. However, current methods for identifying offensive content in such communication largely…