SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.04657 · NeurIPS · 2023

BEAVERTAILS: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

Yaodong Yang, Chi Zhang, Yizhou Wang, Boyuan Chen, Mickel Liu, Xuehai Pan, Jiaming Ji, Juntao Dai, Ce Bian, Ruiyang Sun

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we introduce the BEAVERTAILS dataset, aimed at fostering research on safety alignment in large language models (LLMs). This dataset uniquely separates annotations of helpfulness and harmlessness for question-answering pairs, thus offering distinct perspectives on these crucial attributes. In total, we have gathered safety meta-labels for 333,963 question-answer (QA) pairs and 361,903 pairs of expert comparison data for both the helpfulness and harmlessness metrics. We further showcase applications of BeaverTails in content moderation and reinforcement learning with human feedback (RLHF), emphasizing its potential for practical safety measures in LLMs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2307.04657")
get_code_for_paper("2307.04657")
have("2307.04657")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2307.04657.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2307.04657.svg)](https://syntology.ai/paper/2307.04657)

Connect an agent — have() is free.