73 citations · 148 across the 25 of their papers we have counts for
25 papers
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…
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…
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…
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…
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…
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…
Achievable Fairness on Your Data With Utility Guarantees
Muhammad Faaiz Taufiq, Jean-Francois Ton, Yang Liu
In machine learning fairness, training models that minimize disparity across different sensitive groups often leads to diminished accuracy, a phenomenon known as the fairness-accur…
Measuring and Reducing LLM Hallucination without Gold-Standard Answers
Jiaheng Wei, Yuanshun Yao, Jean-Francois Ton +3
LLM hallucination, i.e. generating factually incorrect yet seemingly convincing answers, is currently a major threat to the trustworthiness and reliability of LLMs. The first step…
Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits
Muhammad Faaiz Taufiq, Arnaud Doucet, Rob Cornish +1
Off-Policy Evaluation (OPE) in contextual bandits is crucial for assessing new policies using existing data without costly experimentation. However, current OPE methods, such as In…
Fair Classifiers that Abstain without Harm
Tongxin Yin, Jean-François Ton, Ruocheng Guo +3
In critical applications, it is vital for classifiers to defer decision-making to humans. We propose a post-hoc method that makes existing classifiers selectively abstain from pred…
Deep Concept Removal
Yegor Klochkov, Jean-Francois Ton, Ruocheng Guo +2
We address the problem of concept removal in deep neural networks, aiming to learn representations that do not encode certain specified concepts (e.g., gender etc.) We propose a no…
Invariant Learning via Probability of Sufficient and Necessary Causes
Mengyue Yang, Zhen Fang, Yonggang Zhang +5
Out-of-distribution (OOD) generalization is indispensable for learning models in the wild, where testing distribution typically unknown and different from the training. Recent meth…
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Yang Liu, Yuanshun Yao, Jean-Francois Ton +6
Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real…
Inference-time Stochastic Ranking with Risk Control
Ruocheng Guo, Jean-François Ton, Yang Liu +1
Learning to Rank (LTR) methods are vital in online economies, affecting users and item providers. Fairness in LTR models is crucial to allocate exposure proportionally to item rele…
Conformal Off-Policy Prediction in Contextual Bandits
Muhammad Faaiz Taufiq, Jean-Francois Ton, Rob Cornish +2
Most off-policy evaluation methods for contextual bandits have focused on the expected outcome of a policy, which is estimated via methods that at best provide only asymptotic guar…
Grassmann Stein Variational Gradient Descent
Xing Liu, Harrison Zhu, Jean-François Ton +2
Stein variational gradient descent (SVGD) is a deterministic particle inference algorithm that provides an efficient alternative to Markov chain Monte Carlo. However, SVGD has been…
Regularized Training of Nearest Neighbor Language Models
Jean-Francois Ton, Walter Talbott, Shuangfei Zhai +1
Including memory banks in a natural language processing architecture increases model capacity by equipping it with additional data at inference time. In this paper, we build upon $…
BayesIMP: Uncertainty Quantification for Causal Data Fusion
Siu Lun Chau, Jean-François Ton, Javier González +2
While causal models are becoming one of the mainstays of machine learning, the problem of uncertainty quantification in causal inference remains challenging. In this paper, we stud…
Meta Learning for Causal Direction
Jean-Francois Ton, Dino Sejdinovic, Kenji Fukumizu
The inaccessibility of controlled randomized trials due to inherent constraints in many fields of science has been a fundamental issue in causal inference. In this paper, we focus…
Robust Pruning at Initialization
Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet +1
Overparameterized Neural Networks (NN) display state-of-the-art performance. However, there is a growing need for smaller, energy-efficient, neural networks tobe able to use machin…
MetaFun: Meta-Learning with Iterative Functional Updates
Jin Xu, Jean-Francois Ton, Hyunjik Kim +2
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a fin…
Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings
Jean-Francois Ton, Lucian Chan, Yee Whye Teh +1
Current meta-learning approaches focus on learning functional representations of relationships between variables, i.e. on estimating conditional expectations in regression. In many…
Automated Model Selection with Bayesian Quadrature
Henry Chai, Jean-Francois Ton, Roman Garnett +1
We present a novel technique for tailoring Bayesian quadrature (BQ) to model selection. The state-of-the-art for comparing the evidence of multiple models relies on Monte Carlo met…
Towards A Unified Analysis of Random Fourier Features
Zhu Li, Jean-Francois Ton, Dino Oglic +1
Random Fourier features is a widely used, simple, and effective technique for scaling up kernel methods. The existing theoretical analysis of the approach, however, remains focused…