EMNLP Findings2025
InfAL: Inference Time Adversarial Learning for Improving Research Ideation
Sikun Guo, Amir Hassan Shariatmadari, Peng Wang, Albert Huang, Aidong Zhang
摘要
Advancements in Large Language Models (LLMs) have opened new opportunities for scientific discovery by assisting researchers in generating novel hypotheses and ideas. In this process, a major challenge is how to optimally and efficiently utilize LLMs' parametric knowledge obtained from their pretraining process. Inspired by Generative Adversarial Networks (GANs), we propose inference time adversarial learning (termed InfAL), implemented through multi-LLM-agent interactions, to enhance research ideation. This approach optimizes the utilization of LLMs' parametric knowledge without requiring additional model training, making adversarial learning efficient and context-driven. To evaluate the quality of generated ideas, we propose a relative quality ranking metric as a scalable alternative to human evaluation. Our results show that InfAL significantly improves idea generation, with GPT-4o achieving a 21% increase in novelty and a 322% increase in feasibility, demonstrating its transformative potential for driving innovation in scientific research.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
脉络
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate 引用了 Can Large Language Models Be an Alternative to Human Evaluations?
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate 引用了 Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Debating with More Persuasive LLMs Leads to More Truthful Answers 引用了 Improving Factuality and Reasoning in Language Models through Multiagent Debate
它引用的 Paper17
- Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum 等ICML 2024 · 1,562 次引用
- An Explanation of In-context Learning as Implicit Bayesian InferenceSang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu MaICLR 2022 · 1,030 次引用
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent DebateChi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu 等ICLR 2024 · 871 次引用
- Can Large Language Models Be an Alternative to Human Evaluations?David Cheng-Han Chiang, Hung-yi LeeACL 2023 · 254 次引用
- Debating with More Persuasive LLMs Leads to More Truthful AnswersAkbir Khan, John Hughes, Dan Valentine, Laura Ruis 等ICML 2024 · 244 次引用
相关 Paper
- Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP ResearchersChenglei Si, Diyi Yang, Tatsunori HashimotoICLR 2025
- Can Large Language Models Unlock Novel Scientific Research Ideas?Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, Asif EkbalEMNLP 2025 · 3 次引用
- NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language ModelsXiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang 等ACL Findings 2025 · 3 次引用
- The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research IdeasChenglei Si, Tatsunori Hashimoto, Diyi YangICLR 2026 · 60 次引用
- Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent SystemHaoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin 等ACL 2025 · 49 次引用
