131 citations · 144 across the 24 of their papers we have counts for
9 papers · 1 filter
Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning
Yu Xia, Zhouhang Xie, Xin Xu +4
Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Exist…
Pluralistic Off-policy Evaluation and Alignment
Chengkai Huang, Junda Wu, Zhouhang Xie +6
Personalized preference alignment for LLMs with diverse human preferences requires evaluation and alignment methods that capture pluralism. Most existing preference alignment datas…
Improving In-Context Learning with Reasoning Distillation
Nafis Sadeq, Xin Xu, Zhouhang Xie +4
Language models rely on semantic priors to perform in-context learning, which leads to poor performance on tasks involving inductive reasoning. Instruction-tuning methods based on…
A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models
Zhouhang Xie, Junda Wu, Yiran Shen +9
Personalized preference alignment for large language models (LLMs), the process of tailoring LLMs to individual users' preferences, is an emerging research direction spanning the a…
Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision
Zhouhang Xie, Tushar Khot, Bhavana Dalvi Mishra +4
Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purp…
Mitigating Hallucination in Fictional Character Role-Play
Nafis Sadeq, Zhouhang Xie, Byungkyu Kang +3
Role-playing has wide-ranging applications in customer support, embodied agents, and computational social science. The influence of parametric world knowledge of large language mod…
Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning
Zhouhang Xie, Bodhisattwa Prasad Majumder, Mengjie Zhao +4
We consider the task of building a dialogue system that can motivate users to adopt positive lifestyle changes: Motivational Interviewing. Addressing such a task requires a system…
Factual and Informative Review Generation for Explainable Recommendation
Zhouhang Xie, Sameer Singh, Julian McAuley +1
Recent models can generate fluent and grammatical synthetic reviews while accurately predicting user ratings. The generated reviews, expressing users' estimated opinions towards re…
Identifying Adversarial Attacks on Text Classifiers
Zhouhang Xie, Jonathan Brophy, Adam Noack +6
The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as Text…