EMNLP Findings2025
InfAL: Inference Time Adversarial Learning for Improving Research Ideation
Sikun Guo, Amir Hassan Shariatmadari, Peng Wang, Albert Huang, Aidong Zhang
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate cites Can Large Language Models Be an Alternative to Human Evaluations?
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate cites Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Debating with More Persuasive LLMs Leads to More Truthful Answers cites Improving Factuality and Reasoning in Language Models through Multiagent Debate
Builds on17
- Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations
- An Explanation of In-context Learning as Implicit Bayesian InferenceSang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu MaICLR 2022 · 1,030 citations
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent DebateChi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu et al.ICLR 2024 · 871 citations
- Can Large Language Models Be an Alternative to Human Evaluations?David Cheng-Han Chiang, Hung-yi LeeACL 2023 · 254 citations
- Debating with More Persuasive LLMs Leads to More Truthful AnswersAkbir Khan, John Hughes, Dan Valentine, Laura Ruis et al.ICML 2024 · 244 citations
Related papers
- 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 citations
- NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language ModelsXiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang et al.ACL Findings 2025 · 3 citations
- The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research IdeasChenglei Si, Tatsunori Hashimoto, Diyi YangICLR 2026 · 60 citations
- Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent SystemHaoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin et al.ACL 2025 · 49 citations
