datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Agent-ValueBench
Agent-ValueBench
Agent-ValueBench constitutes the first comprehensive benchmark dedicated to evaluating the underlying values of autonomous agents. It features 394 executable environments across 16 domains, offering 4,335 value-conflict tasks that span 28 value systems (332 dimensions).
This Hugging Face release contains both structured JSONL tables for dataset viewing and Croissant metadata generation, and the original raw benchmark artifacts.
Repository Structure… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-nips2026/Agent-ValueBench.Agent-ValueBench
Agent-ValueBench
Paper | Project Page | GitHub
Agent-ValueBench is the first comprehensive benchmark dedicated to evaluating the underlying values of autonomous agents. It features 394 executable environments across 16 domains, offering 4,335 value-conflict tasks that span 28 value systems (332 dimensions).
Repository Structure
README.md
data/
cases.jsonl
rubrics.jsonl
environments.jsonl
raw/
case/
rubric/
environment/
Data Files… See the full description on the dataset page: https://huggingface.co/datasets/Value4AI/Agent-ValueBench.when-agents-act
Dataset Card for "When Agents Act"
Dataset Summary
This dataset contains 702 ethical decision judgements from 9 frontier LLMs (Claude Opus 4.5, GPT-5, GPT-5 Nano, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Gemini 2.5 Flash, Grok-4, Grok-4 Fast) across 10 rigorously curated AI-relevant ethical dilemmas. Models were tested in both theory mode (hypothetical reasoning) and action mode (tool-enabled agents believing actions would execute).
Key Finding: Models reverse… See the full description on the dataset page: https://huggingface.co/datasets/values-md/when-agents-act.tw-value-bench
Dataset Card for tw-value-bench
tw-value-bench 是一份針對「臺灣價值觀／文化規範」的繁體中文評測集，用於檢驗大型語言模型對臺灣社會普遍認同之文化、倫理、生活慣例等是否具備一致與適切的判斷能力。資料分為 assay（申論題）、choice（選擇題）、true-false（是非題）三種題型。
Dataset Details
Dataset Description
本資料集設計三種題型以涵蓋不同評估面向：
assay（申論題）：1,501 題。包含 question 與 reference_answer，可用於以 LLM-as-Judge 或文本生成指標評分。
choice（選擇題）：多選一格式，可用於 zero-shot accuracy。
true-false（是非題）：判斷敘述真偽。
題目主題涵蓋臺灣常見的生活情境、文化規範、社會議題、政府制度、節慶風俗等；參考答案以「臺灣讀者普遍可接受」之共識為基準。
授權為 twinkle.ai，請參見 LICENSE。… See the full description on the dataset page: https://huggingface.co/datasets/lianghsun/tw-value-bench.india-medical-value-travel-mvp
India Medical Value Travel (MVT) Platform – MVP Dataset
A comprehensive, structured JSON dataset for building an AI-powered Medical Value Travel platform connecting international patients with Indian hospitals.
Overview
India is a global leader in medical tourism due to 60–80% lower treatment costs vs US/UK, world-class hospital chains, and government support through initiatives like "Heal in India" and e-Medical Visa. This dataset provides the complete data foundation… See the full description on the dataset page: https://huggingface.co/datasets/Dhanush008/india-medical-value-travel-mvp.Think_and_Query_value_for_R1
Introduction
This repository implements a Shapley value-based approach to quantitatively evaluate the contributions of query (q) and think (t) in generating answer (a).
Method
think_value = [loss(a|q) - loss(a|q,t) + loss(a|∅) - loss(a|t)] / 2
query_value = [loss(a|t) - loss(a|q,t) + loss(a|∅) - loss(a|q)] / 2
think_ratio = think_value/loss(a|∅)
query_ratio = query_value/loss(a|∅)
Original dataset… See the full description on the dataset page: https://huggingface.co/datasets/caihuaiguang/Think_and_Query_value_for_R1.