IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?
cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/meta-llama/llama-models
Project page: https://cxcscmu.github.io/IdeaTaste
Terminology
Sources
- Ex Ante Evaluation of AI-Induced Idea Diversity Collapse
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies
- Measuring the Gap Between Human and LLM Research Ideas
- Inconsistency in Conference Peer Review: Revisiting the 2014 NeurIPS Experiment
- A Cognitive Framework for Idea Diversity in Large Language Models
- Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap
- When is an article actually published? An analysis of online availability, publication, and indexation dates
- SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
- Idea2Plan: Exploring AI-Powered Research Planning
- HindSight: Evaluating LLM-Generated Research Ideas via Future Impact
- The Semantic Scholar Open Data Platform
- Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery
- ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
- Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- LLM4SR: A Survey on Large Language Models for Scientific Research
- OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts
- AI Idea Bench 2025: AI Research Idea Generation Benchmark
- Rethinking Literature Search Evaluation: Deep Research Helps, and Human Citation Lists Are Not a Ground Truth
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data