paper-with-me

Papers

Demystifying Prompts in Language Models via Perplexity Estimation

2022-12-08 · Hila Gonen, Srini Iyer, Terra Blevins, Noah A. Smith, Luke Zettlemoyer

Language models can be prompted to perform a wide variety of zero- and few-shot learning problems. However, performance varies significantly with the choice of prompt, and we do not yet understand why this happens or how to pick the best prompts. In this work, we analyze the factors that contribute to this variance and establish a new empirical hypothesis: the performance of a prompt is coupled with the extent to which the model is familiar with the language it contains. Over a wide range of tasks, we show that the lower the perplexity of the prompt is, the better the prompt is able to perform the task. As a result, we devise a method for creating prompts: (1) automatically extend a small seed set of manually written prompts by paraphrasing using GPT3 and backtranslation and (2) choose the lowest perplexity prompts to get significant gains in performance.

📄 PDF Abstract BibTeX arXiv:2212.04037

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learning

Similar Papers 제목 키워드 기반

FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation

2024-06-17 · Bangzheng Li, Ben Zhou, Xingyu Fu, Fei Wang 외

Language models have shown impressive in-context-learning capabilities, which allow them to benefit from input prompts and perform better on downstream end tasks. Existing works investigate the mechanisms behind this obs…

In-Context Learning

Demystifying optimized prompts in language models

2025-05-04 · Rimon Melamed, Lucas H. McCabe, H. Howie Huang

Modern language models (LMs) are not robust to out-of-distribution inputs. Machine generated (``optimized'') prompts can be used to modulate LM outputs and induce specific behaviors while appearing completely uninterpret…

PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models

2024-12-18 · Biao Liu, Wenyi Fang, Xiaoyu Wu, Yang Zheng 외

Pre-trained Vision-Language (VL) models such as CLIP have demonstrated their excellent performance across numerous downstream tasks. A recent method, Context Optimization (CoOp), further improves the performance of VL mo…

Prompt Learning

ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts

2024-07-12 · Amelia F. Hardy, Houjun Liu, Bernard Lange, Duncan Eddy 외

Conventional approaches for the automated red-teaming of large language models (LLMs) aim to identify prompts that elicit toxic outputs from a frozen language model (the defender). This often results in the prompting mod…

Language ModelingLanguage ModellingRed Teaming

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback

2025-10-07 · Raffaele Mura, Giorgio Piras, Kamilė Lukošiūtė, Maura Pintor 외 arxiv

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the m…