Research map / Large language models / Language, safety and interpretability
Whose Opinions Do Language Models Reflect?
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply human feedback (RLHF/instruct) tuning to base models (text-davinci-003 vs davinci) | OpenAI GPT-3 series LMs · OpinionQA representativeness vs overall US population | representativeness score R^O | Hurt |
| Steering LMs toward a demographic group via prompting (QA/BIO/PORTRAY context) | 9 LMs · OpinionQA steerability on 500 contentious questions | group alignment with steering vs default | Helped |
| Steering LMs toward a demographic group via prompting | 9 LMs · OpinionQA steerability | disparity in alignment across groups | No clear effect |
| Refusal option treated separately, measuring refusal rate of HF-tuned models | HF-tuned LMs · OpinionQA refusal rates | refusal rate | No clear effect |
Closest papers by meaning
- The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models (NeurIPS 2024 · similarity 0.88)
- Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes (ICLR 2025 · similarity 0.87)
- Questioning the Survey Responses of Large Language Models (NeurIPS 2024 · similarity 0.87)
- Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models (ICLR 2024 · similarity 0.85)
- Human Feedback is not Gold Standard (ICLR 2024 · similarity 0.85)
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.