Hongli Zhan | 詹弘立

Selected Publications

Visit this page for my complete list of publications, and this page for my patents.

1. ICML 2025

   SPRI: Aligning Large Language Models with Context-Situated Principles

   Hongli Zhan, Muneeza Azmat, Raya Horesh, Junyi Jessy Li, and Mikhail Yurochkin

   In Proceedings of the 42nd International Conference on Machine Learning. 2025. [26.9% acceptance rate (3,260 out of 12,107 submissions); Work started and partially done during my internship at IBM Research]

   Abstract arXiv Open Review Conference View PDF Code Poster Slides Expo Talk Expo Talk Slides

   Aligning Large Language Models to integrate and reflect human values, especially for tasks that demand intricate human oversight, is arduous since it is resource-intensive and time-consuming to depend on human expertise for context-specific guidance. Prior work has utilized predefined sets of rules or principles to steer the behavior of models (Bai et al., 2022; Sun et al., 2023). However, these principles tend to be generic, making it challenging to adapt them to each individual input query or context. In this work, we present Situated-PRInciples (SPRI), a framework requiring minimal or no human effort that is designed to automatically generate guiding principles in real-time for each input query and utilize them to align each response. We evaluate SPRI on three tasks, and show that 1) SPRI can derive principles in a complex domain-specific task that leads to on-par performance as expert-crafted ones; 2) SPRI-generated principles lead to instance-specific rubrics that outperform prior LLM-as-a-judge frameworks; 3) using SPRI to generate synthetic SFT data leads to substantial improvement on truthfulness. We release our code and model generations at https://github.com/honglizhan/SPRI-public.

2. COLM 2024

   Large Language Models are Capable of Offering Cognitive Reappraisal, if Guided

   Hongli Zhan, Allen Zheng, Yoon Kyung Lee, Jina Suh, Junyi Jessy Li, and Desmond Ong

   In Proceedings of the 1st Conference on Language Modeling. 2024. [28.8% acceptance rate (299 out of 1,036 submissions)]

   Abstract arXiv Open Review Conference View PDF Code Poster

   Large language models (LLMs) have offered new opportunities for emotional support, and recent work has shown that they can produce empathic responses to people in distress. However, long-term mental well-being requires emotional self-regulation, where a one-time empathic response falls short. This work takes a first step by engaging with cognitive reappraisals, a strategy from psychology practitioners that uses language to targetedly change negative appraisals that an individual makes of the situation; such appraisals is known to sit at the root of human emotional experience. We hypothesize that psychologically grounded principles could enable such advanced psychology capabilities in LLMs, and design RESORT which consists of a series of reappraisal constitutions across multiple dimensions that can be used as LLM instructions. We conduct a first-of-its-kind expert evaluation (by clinical psychologists with M.S. or Ph.D. degrees) of an LLM’s zero-shot ability to generate cognitive reappraisal responses to medium-length social media messages asking for support. This fine-grained evaluation showed that even LLMs at the 7B scale guided by RESORT are capable of generating empathic responses that can help users reappraise their situations.