1 citations · 4 across the 12 of their papers we have counts for
13 papers
Steering Language Model Goals with Value Transplant
Pengcheng Jiang, Fabien Roger
Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes. Previo…
MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry
Joey Chan, Wonbin Kweon, Ashley Shin +4
Large language models (LLMs) have shown promise for molecular property prediction, but their ability to reason over chemical structures remains limited, as molecular representation…
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
Pengcheng Jiang, Judith Yue Li, Moonkyung Ryu +8
Many modern retrieval problems are set-valued: given a broad intent, the system must return a collection of results that optimizes higher-order properties (e.g., diversity, coverag…
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
Pengrui Han, Xueqiang Xu, Keyang Xuan +12
Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely…
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang +13
Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retr…
Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering
Jash Rajesh Parekh, Wonbin Kweon, Joey Chan +7
Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every…
Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi +31
Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learnin…
RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
Lang Qin, Zijian Gan, Xu Cao +5
Computational drug repurposing for rare diseases is especially challenging when no prior associations exist between drugs and target diseases. Therefore, knowledge graph completion…
GRACE: Generative Representation Learning via Contrastive Policy Optimization
Jiashuo Sun, Shixuan Liu, Zhaochen Su +6
Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and…
PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval
Wonbin Kweon, Runchu Tian, SeongKu Kang +4
Scientific document retrieval is a critical task for enabling knowledge discovery and supporting research across diverse domains. However, existing dense retrieval methods often st…
Topic Coverage-based Demonstration Retrieval for In-Context Learning
Wonbin Kweon, SeongKu Kang, Runchu Tian +3
The effectiveness of in-context learning relies heavily on selecting demonstrations that provide all the necessary information for a given test input. To achieve this, it is crucia…
Structure-Augmented Reasoning Generation
Jash Rajesh Parekh, Pengcheng Jiang, Jiawei Han
Recent advances in Large Language Models (LLMs) have significantly improved complex reasoning capabilities. Retrieval-Augmented Generation (RAG) has further extended these capabili…
Zero-Shot Open-Schema Entity Structure Discovery
Xueqiang Xu, Jinfeng Xiao, James Barry +7
Entity structure extraction, which aims to extract entities and their associated attribute-value structures from text, is an essential task for text understanding and knowledge gra…