activity
20172025
most citedTrustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

73 citations · 109 across the 19 of their papers we have counts for

collaborators

23 papers

cs.MA2025

How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs

Andrew Estornell, Jean-Francois Ton, Muhammad Faaiz Taufiq +1

Large Language Models (LLMs) have achieved strong performance on a wide range of complex reasoning tasks, yet further gains are often possible by leveraging the complementary stren…

cs.CL2024★ 1 cited

Understanding Chain-of-Thought in LLMs through Information Theory

Jean-Francois Ton, Muhammad Faaiz Taufiq, Yang Liu

Large Language Models (LLMs) have shown impressive performance in complex reasoning tasks through the use of Chain-of-Thought (CoT) reasoning, allowing models to break down problem…

cs.AI2024

Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives

Hao Sun, Yunyi Shen, Jean-Francois Ton

The Bradley-Terry (BT) model is a common and successful practice in reward modeling for Large Language Model (LLM) alignment. However, it remains unclear why this model -- original…

cs.CL2024★ 1 cited

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

Andrew Estornell, Jean-Francois Ton, Yuanshun Yao +1

Large language models (LLMs) have demonstrated a remarkable ability to serve as general-purpose tools for various language-based tasks. Recent works have demonstrated that the effi…

cs.LG2024★ 1 cited

Conformal Counterfactual Inference under Hidden Confounding

Zonghao Chen, Ruocheng Guo, Jean-François Ton +1

Personalized decision making requires the knowledge of potential outcomes under different treatments, and confidence intervals about the potential outcomes further enrich this deci…

cs.LG2024★ 1 cited

Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation

Xiaoying Zhang, Jean-Francois Ton, Wei Shen +2

We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for L…