Papers by Xia Ning
\mathtt{GeLLM^3O}: Generalizing Large Language Models for Multi-property Molecule Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have remarkable out-of-domain generalizability to novel optimization tasks. |
| Approach: | They propose a series of instruction-tuned LLMs for molecule optimization that outperform state-of-the-art instruction-based LLM models. |
| Outcome: | mathttMuMOInstruct outperforms state-of-the-art LLMs on 5 in-domain and 5 out-of domain tasks. |
Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving (2025.findings-naacl)
Copied to clipboard
Botao Yu, Frazier N. Baker, Ziru Chen, Garrett Herb, Boyu Gou, Daniel Adu-Ampratwum, Xia Ning, Huan Sun
| Challenge: | Existing evaluations of large language models (LLMs) with tools are limited and qualitative . existing evaluations have been limited and only focus on 14 tasks focusing on compound synthesis. |
| Approach: | They propose to develop an enhanced chemistry agent over ChemCrow to improve chemistry problem solving by integrating tools into LLMs. |
| Outcome: | The proposed agent does not consistently outperform its base LLMs without tools on specialized chemistry tasks and general chemistry questions. |
Planning with Diffusion Models for Target-Oriented Dialogue Systems (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for directing conversations toward specific targets generate dialogue plans in a step-by-step sequential manner and suffer from compounding errors and myopic actions. |
| Approach: | They propose a framework that leverages diffusion models to enable non-sequential dialogue planning. |
| Outcome: | The proposed framework performs non-myopic lookahead exploration and optimizes action strategies over a long horizon through non-sequential dialogue planning. |
Entity Decomposition with Filtering: A Zero-Shot Clinical Named Entity Recognition Framework (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that large language models (LLMs) can perform in named entity recognition tasks. |
| Approach: | They propose a framework for clinical named entity recognition that decomposes the entity recognition task into several retrievals of sub-types and then filters them. |
| Outcome: | The proposed framework improves on the clinical named entity recognition task. |
LIDDIA: Language-based Intelligent Drug Discovery Agent (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in artificial intelligence for chemistry have sought to expedite individual drug discovery tasks. |
| Approach: | They propose an autonomous agent capable of intelligently navigating the drug discovery process in silico. |
| Outcome: | The proposed agent can generate molecules meeting key pharmaceutical criteria on over 70% of 30 clinically relevant targets and intelligently balances exploration and exploitation in the chemical space. |
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)
Copied to clipboard
Yifei Li, Hanane Nour Moussa, Ziru Chen, Shijie Chen, Botao Yu, Mingyi Xue, Benjamin Burns, Tzu-Yao Chiu, Vishal Dey, Zitong Lu, Chen Wei, Qianheng Zhang, Tianyu Zhang, Song Gao, Xuhui Huang, Xia Ning, Nesreen K. Ahmed, Ali Payani, Huan Sun
| Challenge: | AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery. |
| Approach: | They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows. |
| Outcome: | The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages. |
SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Search (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods train RL-based agents with greedy action selection or sampling strategy and suffer from suboptimal conversational planning. |
| Approach: | They propose a Monte Carlo Tree Search-based CRS framework called SAPIENT . it consists of a conversational agent and a communication planner . |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on four benchmark datasets. |
Large Language Models for Controllable Multi-property Multi-objective Molecule Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for molecule optimization fail to capture property-specific objectives . a series of instruction-tuned LLMs can perform targeted property-specific optimization . |
| Approach: | They propose a set of instruction-tuned LLMs that can perform targeted property-specific optimization. |
| Outcome: | a new instruction-tuned LLM can perform targeted property-specific optimization. |