Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules. Whether such an output that appears creative is truly original and effective is hard to establish: open-ended outputs require subjective judgment, the output may replicate something seen in training, or the task may...
Eric Xie, Wenqian Ye, Ai-Dong Zhang· 1 citation· ⚡1
Scientific ideation is driven by curiosity: researchers ask questions that expose knowledge gaps, reveal competing hypotheses, and clarify missing evidence relevant to decision making. Yet, most LLM-based ideation systems optimize the idea text while leaving curiosity under-modeled, resulting in brittle, engine-specifi...
Sikun Guo, Di Wang, Xiaohan Fan et al.· Proceedings of the 32nd ACM...· 0 citations
Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent d...
Bo Yuan, Wenqian Ye, Ze-Lin Zhao et al.· 0 citations
It is shown that current large language models generally perform poorly on most of the safety tests, regardless of their safety alignment mechanisms, which underscores the crucial need for ongoing human oversight and the implementation of strict safety guardrails before deploying these tools in clinical practice.
Yi-Fan Yang, Qiao Jin, Robert Leaman et al.· Communications Medicine· 0 citations
Concept-Residual eXpansion (CRX), a concept-augmented framework that improves robustness by expanding the set of candidate predictive features by improving robustness to spurious correlations, is proposed.
Eric Xie, Guang-Zhi Xiong, Wenqian Ye et al.· Proceedings of the 32nd ACM...· 0 citations
InfRL (Inference-time Reinforcement Learning) offers a practical and domain-agnostic approach to harness reinforcement learning during inference, bridging the gap between static prompting and computationally intensive parameter-level fine-tuning.
Sikun Guo, Amir Hassan Shariatmadari, Jiuqi Wang et al.· Proceedings of the 32nd ACM...· 0 citations
Scientific ideation is driven by curiosity: researchers ask questions that expose knowledge gaps, reveal competing hypotheses, and clarify missing evidence relevant to decision making. Yet, most LLM-based ideation systems optimize the idea text while leaving curiosity under-modeled, resulting in brittle, engine-specifi...
Sikun Guo, Di Wang, Xiaohan Fan et al.· Proceedings of the 32nd ACM...· 0 citations
Large language models (LLMs) possess extensive latent knowledge yet remain largely static at inference. Once prompted, their generation policy typically cannot evolve, and post-hoc ''self-reflection'' methods provide no explicit principled learning signals. To address this limitation, we formally model iterative resear...
Sikun Guo, Amir Hassan Shariatmadari, Jiuqi Wang et al.· Proceedings of the 32nd ACM...· 0 citations
Concept-Residual eXpansion (CRX), a concept-augmented framework that improves robustness by expanding the set of candidate predictive features by improving robustness to spurious correlations, is proposed.
Eric Xie, Guangzhi Xiong, Wenqian Ye et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
