ninoscherrer/moralchoice
收藏资源简介:
--- pretty_name: MoralChoice license: cc-by-4.0 language: - en size_categories: - 1K<n<10K --- # Dataset Card for MoralChoice - **Homepage:** Coming Soon - **Paper:** Coming soon - **Repository:** [https://github.com/ninodimontalcino/moralchoice](https://github.com/ninodimontalcino/moralchoice) - **Point of Contact:** [Nino Scherrer & Claudia Shi](mailto:nino.scherrer@gmail.com,claudia.j.shi@gmail.com?subject=[MoralChoice]) ### Dataset Summary *MoralChoice* is a survey dataset to evaluate the moral beliefs encoded in LLMs. The dataset consists of: - **Survey Question Meta-Data:** 1767 hypothetical moral scenarios where each scenario consists of a description / context and two potential actions - **Low-Ambiguity Moral Scenarios (687 scenarios):** One action is clearly preferred over the other. - **High-Ambiguity Moral Scenarios (680 scenarios):** Neither action is clearly preferred - **Survey Question Templates:** 3 hand-curated question templates - **Survey Responses:** Outputs from 28 open- and closed-sourced LLMs A statistical workflow for analyzing the survey responses can be found in the corresponding [paper](). 🚧 **Important**: 🚧 - *Moral scenarios* and *question templates* are already available. - *Survey responses* will be uploaded shortly! ### Languages *MoralChoice* is only available in English. ## Dataset Structure ### Data Fields #### Moral Scenarios (Survey Question Meta-Data) ``` - scenario_id unique scenario identifier - ambiguity level of ambiguity (low or high) - generation_type generation type (hand-written or generated) - context scenario description / contextualization - action 1 description of a potential action - action 2 description of a potential action - a1_{rule} {rule} violation label of action 1 - a2_{rule} {rule} violation label of action 2 ``` #### Survey Question Templates ``` - name name of question template (e.g., ab, repeat, compare) - question_header question instruction header text - question question template with placeholders ``` #### Survey Responses ``` - scenario_id unique scenario identifier - model_id model identifier (e.g., openai/gpt-4) - question_type question type (ab: A or B?, repeat: Repeat the preferred answer, compare: Do you prefer A over B? ) - question_ordering question ordering label (0: default order, 1: flipped order) - question_header question instruction header text - question_text question text - answer_raw raw answer of model - decision semantic answer of model (e.g., action1, action2, refusal, invalid) - eval_technique evaluation technique used - eval_top_p evaluation parameter - top_p - eval_temperature evaluation parameter - temperature - timestamp timestamp of model access ``` ## Dataset Creation ### Generation of Moral Scenarios The construction of *MoralChoice* follows a three-step procedure: - **Scenario Generation:** We generate seperately low- and high-ambiguity scenarios (i.e., the triple of scenario context, action 1 and action 2) guided by the 10 rules of Gert's common morality framework. - **Low-Ambiguity Scenarios:** Zero-Shot Prompting Setup based on OpenAI's gpt-4 - **High-Ambiguity Scenarios:** Stochastic Few-Shot Prompting Setup based on OpenAI's text-davinci-003 using a a set of 100 hand-written scenarios - **Scenario Curation:** We check the validity and grammar of each generated scenario manually and remove invalid scenarios. In addition, we assess lexical similarity between the generated scenarios and remove duplicates and overly-similar scenarios. - **Auxiliarly Label Aquisition:** We acquire auxiliary rule violation labels through SurgeAI for every scenario. For detailed information, we refer to the corresponding paper. ## Collection of LLM responses Across all models, we employ **temperature-based sampling** with `top-p=1.0`and `temperature=1.0`. For every specific question form (unique combination of scenario, question template, answer option ordering), we collect multiple samples (5 for low-ambiguity scenarios and 10 for high-ambiguity scenarios). The raw sequence of token outputs were mapped to semantic action (see the corresponding paper for exact details). ### Annotations To acquire high-quality annotations, we employ experienced annotators sourced through the data-labeling company [Surge AI](https://www.surgehq.ai/). ## Considerations for Using the Data - Limited Diversity in Scenarios (professions, contexts) - Limited Diversity in Question-Templates - Limited to English ### Dataset Curators - Nino Scherrer ([Website](https://ninodimontalcino.github.io/), [Mail](mailto:nino.scherrer@gmail.com?subject=[MoralChoice])) - Claudia Shi ([Website](https://www.claudiajshi.com/), [Mail](mailto:nino.scherrer@gmail.com?subject=[MoralChoice])) ### Citation ``` @misc{scherrer2023moralchoice, title={Evaluating the Moral Beliefs Encoded in LLMs}, author={Scherrer, Nino and Shi, Claudia, and Feder, Amir and Blei, David}, year={2023}, journal={arXiv:} } ```
--- pretty_name: 道德选择(MoralChoice) license: CC-BY-4.0(知识共享署名4.0许可) language: - 英语 size_categories: - 1000 < n < 10000 --- # 道德选择(MoralChoice)数据集卡片 - **主页**:即将上线 - **论文**:即将发布 - **代码仓库**:[https://github.com/ninodimontalcino/moralchoice](https://github.com/ninodimontalcino/moralchoice) - **联系人**:[尼诺·舍雷尔(Nino Scherrer)与克劳迪娅·施(Claudia Shi)](mailto:nino.scherrer@gmail.com,claudia.j.shi@gmail.com?subject=[MoralChoice]) ### 数据集概述 道德选择(MoralChoice)是用于评估大语言模型(LLM)所编码的道德信念的调研数据集。该数据集包含以下内容: - **调研问题元数据**:1767个假设性道德场景,每个场景由一段描述/上下文与两种可选行动构成 - **低歧义道德场景(687个)**:其中一种行动明显更受青睐 - **高歧义道德场景(680个)**:两种行动均无明显偏好 - **调研问题模板**:3个人工精心编制的问题模板 - **调研回复**:28个开源与闭源大语言模型的输出结果 分析调研回复的标准化统计流程可参见对应[论文]()。 🚧 **重要提示**: 🚧 - 道德场景与问题模板已可公开获取。 - 调研回复即将上传! ### 语言支持 道德选择(MoralChoice)仅提供英文版本。 ## 数据集结构 ### 数据字段 #### 道德场景(调研问题元数据) - scenario_id 唯一场景标识符 - ambiguity 歧义等级(低或高) - generation_type 生成类型(手写或模型生成) - context 场景描述/上下文说明 - action 1 可选行动1的描述 - action 2 可选行动2的描述 - a1_{rule} 行动1的{rule}违规标签 - a2_{rule} 行动2的{rule}违规标签 #### 调研问题模板 - name 问题模板名称(例如ab、repeat、compare) - question_header 问题指令头部文本 - question 带有占位符的问题模板 #### 调研回复 - scenario_id 唯一场景标识符 - model_id 模型标识符(例如openai/gpt-4) - question_type 问题类型(ab:选择A或B?;repeat:重复偏好的答案;compare:你是否更偏好A而非B?) - question_ordering 问题顺序标签(0:默认顺序;1:翻转顺序) - question_header 问题指令头部文本 - question_text 问题文本 - answer_raw 模型的原始回复 - decision 模型的语义化回复(例如action1、action2、拒绝、无效) - eval_technique 所用的评估技术 - eval_top_p 评估参数——top_p - eval_temperature 评估参数——temperature - timestamp 模型访问时间戳 ## 数据集构建 ### 道德场景的生成 道德选择(MoralChoice)的构建遵循三步流程: - **场景生成**:基于格特(Gert)提出的10条共同道德框架准则,分别生成低歧义与高歧义场景(即场景上下文、行动1与行动2的三元组) - **低歧义场景**:基于OpenAI的GPT-4的零样本(Zero-Shot)提示设置 - **高歧义场景**:基于OpenAI的text-davinci-003的随机少样本(Stochastic Few-Shot)提示设置,以100个手写场景作为示例集 - **场景审核**:人工审核每个生成场景的有效性与语法,剔除无效场景。此外,评估生成场景间的词汇相似度,移除重复与过度相似的场景。 - **辅助标签获取**:通过SurgeAI为每个场景获取辅助的规则违规标签。 详细信息可参见对应论文。 ### 大语言模型回复收集 针对所有模型,我们采用**基于温度的采样**策略,设置`top-p=1.0`与`temperature=1.0`。针对每种特定的问题形式(场景、问题模板与答案选项顺序的唯一组合),我们收集多个样本(低歧义场景为5个,高歧义场景为10个)。原始Token输出序列被映射为语义化行动(详细细节参见对应论文)。 #### 标注流程 为获取高质量标注,我们通过数据标注公司[Surge AI](https://www.surgehq.ai/)聘请资深标注人员完成标注工作。 ## 数据使用注意事项 - 场景多样性有限(覆盖职业、上下文维度不足) - 问题模板多样性有限 - 仅支持英文 ## 数据集负责人 - 尼诺·舍雷尔(Nino Scherrer)([个人网站](https://ninodimontalcino.github.io/), [邮箱](mailto:nino.scherrer@gmail.com?subject=[MoralChoice])) - 克劳迪娅·施(Claudia Shi)([个人网站](https://www.claudiajshi.com/), [邮箱](mailto:claudia.j.shi@gmail.com?subject=[MoralChoice])) ## 引用 bibtex @misc{scherrer2023moralchoice, title={评估大语言模型所编码的道德信念}, author={Scherrer, Nino and Shi, Claudia, and Feder, Amir and Blei, David}, year={2023}, journal={arXiv:} }
数据集概述
数据集名称: MoralChoice
许可证: cc-by-4.0
语言: 仅限英语
数据集大小: 1K<n<10K
数据集内容
数据组成:
- 调查问题元数据(道德场景): 1767个假设的道德场景,包括687个低模糊性场景和680个高模糊性场景。
- 调查问题模板: 3个手工策划的问题模板。
- 调查响应: 来自28个开放源和闭源LLM的输出。
数据字段:
- 道德场景(调查问题元数据): 包括场景ID、模糊性、生成类型、上下文、两个潜在行动及其规则违反标签。
- 调查问题模板: 包括模板名称、问题标题和问题模板。
- 调查响应: 包括场景ID、模型ID、问题类型、问题顺序、问题标题、问题文本、原始答案、决策、评估技术、评估参数和时间戳。
数据集创建
道德场景生成:
- 低模糊性场景: 使用基于OpenAI的gpt-4的零样本提示设置生成。
- 高模糊性场景: 使用基于OpenAI的text-davinci-003的随机少样本提示设置生成。
场景精选:
- 手动检查每个生成场景的有效性和语法,并移除无效场景。
- 评估生成场景之间的词汇相似性,移除重复和过于相似的场景。
辅助标签获取:
- 通过SurgeAI获取每个场景的辅助规则违反标签。
使用注意事项
- 场景多样性有限: 职业和情境的多样性有限。
- 问题模板多样性有限: 问题模板数量有限。
- 语言限制: 仅限英语。




