paper-with-me

홈 › Papers

Validating Large Language Models with ReLM

2022-11-21 · Michael Kuchnik, Virginia Smith, George Amvrosiadis

Although large language models (LLMs) have been touted for their ability to generate natural-sounding text, there are growing concerns around possible negative effects of LLMs such as data memorization, bias, and inappropriate language. Unfortunately, the complexity and generation capacities of LLMs make validating (and correcting) such concerns difficult. In this work, we introduce ReLM, a system for validating and querying LLMs using standard regular expressions. ReLM formalizes and enables a broad range of language model evaluations, reducing complex evaluation rules to simple regular expression queries. Our results exploring queries surrounding memorization, gender bias, toxicity, and language understanding show that ReLM achieves up to 15x higher system efficiency, 2.5x data efficiency, and increased statistical and prompt-tuning coverage compared to state-of-the-art ad-hoc queries. ReLM offers a competitive and general baseline for the increasingly important problem of LLM validation.

📄 PDF Abstract BibTeX arXiv:2211.15458

Code (1)

mkuchnik/relm 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingMemorization

Similar Papers 제목 키워드 기반

Replicating ReLM Results: Validating Large Language Models with ReLM

2025-04-16 · Reece Adamson, Erin Song

Validating Large Language Models with ReLM explores the application of formal languages to evaluate and control Large Language Models (LLMs) for memorization, bias, and zero-shot performance. Current approaches for evalu…

Memorization

The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community

2024-08-15 · Shachar Don-Yehiya, Leshem Choshen, Omri Abend

Human-model conversations provide a window into users' real-world scenarios, behavior, and needs, and thus are a valuable resource for model development and research. While for-profit companies collect user data through …

ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction

2023-10-20 · Yaorui Shi, An Zhang, Enzhi Zhang, Zhiyuan Liu 외

Predicting chemical reactions, a fundamental challenge in chemistry, involves forecasting the resulting products from a given reaction process. Conventional techniques, notably those employing Graph Neural Networks (GNNs…

Chemical Reaction PredictionPrediction

NatureLM: Deciphering the Language of Nature for Scientific Discovery

2025-02-11 · Yingce Xia, Peiran Jin, Shufang Xie, Liang He 외

Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation mod…

Drug DiscoveryRetrosynthesisscientific discovery

NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics

2024-11-11 · David Robinson, Marius Miron, Masato Hagiwara, Olivier Pietquin

Large language models (LLMs) prompted with text and audio represent the state of the art in various auditory tasks, including speech, music, and general audio, showing emergent abilities on unseen tasks. However, these c…

zero-shot-classificationZero-Shot Learning