The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

• URL: http://arxiv.org/abs/2404.16019v1
• Date: Wed, 24 Apr 2024 17:51:36 GMT
• Title: The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
• Authors: Hannah Rose Kirk, Alexander Whitefield, Paul Röttger, Andrew Bean, Katerina Margatina, Juan Ciro, Rafael Mosquera, Max Bartolo, Adina Williams, He He, Bertie Vidgen, Scott A. Hale,
• Abstract summary: We introduce PRISM, a new dataset which maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries. PRISM contributes (i) wide geographic and demographic participation in human feedback data; (ii) two census-representative samples for understanding collective welfare (UK and US); and (iii) individualised feedback where every rating is linked to a detailed participant profile.
• Score: 67.38144169029617
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human feedback plays a central role in the alignment of Large Language Models (LLMs). However, open questions remain about the methods (how), domains (where), people (who) and objectives (to what end) of human feedback collection. To navigate these questions, we introduce PRISM, a new dataset which maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries, to their contextual preferences and fine-grained feedback in 8,011 live conversations with 21 LLMs. PRISM contributes (i) wide geographic and demographic participation in human feedback data; (ii) two census-representative samples for understanding collective welfare (UK and US); and (iii) individualised feedback where every rating is linked to a detailed participant profile, thus permitting exploration of personalisation and attribution of sample artefacts. We focus on collecting conversations that centre subjective and multicultural perspectives on value-laden and controversial topics, where we expect the most interpersonal and cross-cultural disagreement. We demonstrate the usefulness of PRISM via three case studies of dialogue diversity, preference diversity, and welfare outcomes, showing that it matters which humans set alignment norms. As well as offering a rich community resource, we advocate for broader participation in AI development and a more inclusive approach to technology design.

Related papers

• Language Model Alignment in Multilingual Trolley Problems [138.5684081822807]
  Building on the Moral Machine experiment, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP. Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions. We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems.
  arXiv  Detail & Related papers  (2024-07-02T14:02:53Z)
• Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback [8.04095222893591]
  We find significant gaps in fairness preferences depending on the race, age, political stance, educational level, and LGBTQ+ identity of annotators. We also demonstrate that demographics mentioned in text have a strong influence on how users perceive individual fairness in moderation.
  arXiv  Detail & Related papers  (2024-06-09T19:42:25Z)
• CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models [59.22460740026037]
  "CIVICS: Culturally-Informed & Values-Inclusive Corpus for Societal impacts" dataset is designed to evaluate the social and cultural variation of Large Language Models (LLMs) We create a hand-crafted, multilingual dataset of value-laden prompts which address specific socially sensitive topics, including LGBTQI rights, social welfare, immigration, disability rights, and surrogacy.
  arXiv  Detail & Related papers  (2024-05-22T20:19:10Z)
• D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation [5.9053106775634685]
  We introduce the dataset: a large-scale cross-cultural dataset of parallel annotations for offensive language in over 4.5K sentences annotated by a pool of over 4k annotators. The dataset contains annotators' moral values captured along six moral foundations: care, equality, proportionality, authority, loyalty, and purity. Our analyses reveal substantial regional variations in annotators' perceptions that are shaped by individual moral values.
  arXiv  Detail & Related papers  (2024-04-16T19:12:03Z)
• Investigating Cultural Alignment of Large Language Models [10.738300803676655]
  We show that Large Language Models (LLMs) genuinely encapsulate the diverse knowledge adopted by different cultures. We quantify cultural alignment by simulating sociological surveys, comparing model responses to those of actual survey participants as references. We introduce Anthropological Prompting, a novel method leveraging anthropological reasoning to enhance cultural alignment.
  arXiv  Detail & Related papers  (2024-02-20T18:47:28Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• UltraFeedback: Boosting Language Models with Scaled AI Feedback [99.4633351133207]
  We present textscUltraFeedback, a large-scale, high-quality, and diversified AI feedback dataset. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models.
  arXiv  Detail & Related papers  (2023-10-02T17:40:01Z)
• Towards Measuring the Representation of Subjective Global Opinions in Language Models [26.999751306332165]
  Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. We develop a quantitative framework to evaluate whose opinions model-generated responses are more similar to. We release our dataset for others to use and build on.
  arXiv  Detail & Related papers  (2023-06-28T17:31:53Z)
• Vyaktitv: A Multimodal Peer-to-Peer Hindi Conversations based Dataset for Personality Assessment [50.15466026089435]
  We present a novel peer-to-peer Hindi conversation dataset- Vyaktitv. It consists of high-quality audio and video recordings of the participants, with Hinglish textual transcriptions for each conversation. The dataset also contains a rich set of socio-demographic features, like income, cultural orientation, amongst several others, for all the participants.
  arXiv  Detail & Related papers  (2020-08-31T17:44:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.