Research map / Large language models / AI and society
SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing
Anjali Parashar, Yingke Li, Eric Yang Yu, Fei Chen, James Neidhoefer, Devesh Upadhyay, Chuchu Fan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add the preference term to the acquisition function (versus mutual-information terms only) (ablation) | SEED-SET HVGP · Fire Rescue | preference score | Improved |
| add the mutual-information exploration terms to preference-only acquisition (ablation) | SEED-SET HVGP · Fire Rescue | preference score | Improved |
| use hierarchical GP instead of a single end-to-end preferential GP | SEED-SET · Power Grid 30-Bus | preference score | Improved |
| vary LLM temperature, prompt wording and evaluator model (ablation) | SEED-SET · Fire Rescue | preference score | No clear effect |
Closest papers by meaning
- Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs (NeurIPS 2026 · similarity 0.83)
- Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering with Generative Optimization (NeurIPS 2026 · similarity 0.82)
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents (NeurIPS 2026 · similarity 0.82)
- ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence (NeurIPS 2026 · similarity 0.82)
- AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite (ICLR 2026 · similarity 0.82)
- Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm (AAAI 2026 · similarity 0.82)
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.
