paper-with-me

홈 › Papers

LLMs learn scientific taste from institutional traces across the social sciences

2026-03-17 · Ziqin Gong, Ning Li, Huaikang Zhou arxiv

Reinforcement-learned reasoning has powered recent AI leaps on verifiable tasks, including mathematics, code, and structure prediction. The harder bottleneck is evaluative judgment in low-verifiability domains, where no oracle anchors reward and the core question is which untested ideas deserve attention. We test whether institutional traces, the record of what fields published, where, and at which tier, can serve as a training signal for AI evaluators. Across eight social science disciplines (psychology, economics, communication, sociology, political science, management, business and finance, public administration), we built held-out four-tier research-pitch benchmarks and supervised-fine-tuned (SFT) LLMs on field-specific publication outcomes. The fine-tuned models cleared the 25 percent chance baseline and exceeded frontier-model performance by wide margins, with best single-model accuracy ranging from 55.0 percent in public administration to 85.5 percent in psychology. In management, evaluated against 48 expert gatekeepers, 174 junior researchers, and 11 frontier reasoning models, the best single fine-tuned model (Qwen3-4B) reached 59.2 percent, 17.6 percentage points above expert majority vote (41.6 percent, non-tied) and 28.1 percentage points above the frontier mean (31.1 percent). The fine-tuned models also showed calibrated confidence: confidence rose when predictions were correct and fell when wrong, mirroring how a skilled reviewer can say "I'm sure" versus "I'm guessing." Selective triage on this signal reached very high accuracy on the highest-confidence subsets in every field. Institutional traces, we conclude, encode a scalable training signal for the low-verifiability judgment on which science depends.

📄 PDF Abstract BibTeX arXiv:2603.16659

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AI Can Learn Scientific Taste

2026-03-15 · Jingqi Tong, Mingzhe Li, Hangcheng Li, Yongzhuo Yang 외 arxiv

Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with the potential for long-term scientific impact. Scientific taste is larg…

Reinforcement Learning

Do Large Language Models Encode Institutional Experience? Evidence from Cross-Linguistic Moral Reasoning Under Ambiguity

2026-05-29 · Nattavudh Powdthavee arxiv

Large language models (LLMs) exhibit systematic differences in moral reasoning across languages, yet the source of this variation remains unclear. We test the hypothesis that languages encode aspects of the institutional…

COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learning

2026-08-31 · Shrinidhi Kumbhar Santosh Mashetty Divij Handa Kevin Coutinho, Siddharth Sambhaji Ghule, Chitta Baral arxiv

Large Language Models (LLMs) trained on extensive scientific research are increasingly integrated as assistants for scientific discovery. However, most research papers omit the fine-grained cognitive process of examining…

Reinforcement Learning

MACC: Multi-Agent Collaborative Competition for Scientific Exploration

2026-03-04 · Satoshi Oyama, Yuko Sakurai, Hisashi Kashima arxiv

Scientific discovery still relies heavily on the manual efforts of individual researchers, leading to limited exploration, redundant trials, and reduced reproducibility. Human-participant data analysis competitions gener…

A Multimodal Symphony: Integrating Taste and Sound through Generative AI

2025-03-04 · Matteo Spanio, Massimiliano Zampini, Antonio Rodà, Franco Pierucci

In recent decades, neuroscientific and psychological research has traced direct relationships between taste and auditory perceptions. This article explores multimodal generative models capable of converting taste informa…

Music Generation