paper-with-me

홈 › Papers

Evaluating Generalization and Representation Stability in Small LMs via Prompting, Fine-Tuning and Out-of-Distribution Prompts

2025-06-16 · Rahul Raja, Arpita Vats

We investigate the generalization capabilities of small language models under two popular adaptation paradigms: few-shot prompting and supervised fine-tuning. While prompting is often favored for its parameter efficiency and flexibility, it remains unclear how robust this approach is in low-resource settings and under distributional shifts. This paper presents a comparative study of prompting and fine-tuning across task formats, prompt styles, and model scales, with a focus on their behavior in both in-distribution and out-of-distribution (OOD) settings. Beyond accuracy, we analyze the internal representations learned by each approach to assess the stability and abstraction of task-specific features. Our findings highlight critical differences in how small models internalize and generalize knowledge under different adaptation strategies. This work offers practical guidance for model selection in low-data regimes and contributes empirical insight into the ongoing debate over prompting versus fine-tuning. Code for the experiments is available at the following

📄 PDF Abstract BibTeX arXiv:2506.17289

Code (0)

등록된 구현이 없습니다.

Tasks

Model Selection

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Representational and Behavioral Stability of Truth in Large Language Models

2025-11-24 · Samantha Dies, Courtney Maynard, Germans Savcisens, Tina Eliassi-Rad arxiv

Large language models (LLMs) are increasingly used as information sources, yet small changes in semantic framing can destabilize their truth judgments. We propose P-StaT (Perturbation Stability of Truth), an evaluation f…

Prompting is not a substitute for probability measurements in large language models

2023-05-22 · Jennifer Hu, Roger Levy

Prompting is now a dominant method for evaluating the linguistic knowledge of large language models (LLMs). While other methods directly read out models' probability distributions over strings, prompting requires models …

Noisy Channel Language Model Prompting for Few-Shot Text Classification

2021-08-09 · ACL 2022 5 · Sewon Min, Mike Lewis, Hannaneh Hajishirzi, Luke Zettlemoyer

We introduce a noisy channel approach for language model prompting in few-shot text classification. Instead of computing the likelihood of the label given the input (referred as direct models), channel models compute the…

AttributeClassificationFew-Shot LearningFew-Shot Text Classification+4

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

2026-02-05 · Rohan Subramanian Thomas, Shikhar Shiromani, Abdullah Chaudhry, Ruizhe Li 외 arxiv

Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified…

Prompt Engineering

A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems

2026-02-03 · Ronald Katende arxiv

Modern learning systems often interpolate training data while still generalizing well, yet it remains unclear when algorithmic stability explains this behavior. We model training as a function-space trajectory and measur…