93 citations · 129 across the 29 of their papers we have counts for
33 papers
Latent space bias directions in LLMs capture confidence, not fairness
Stephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban +1
Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models. However, prior work reports that steering vectors generalis…
Fairness-Aware Test-Time Prompt Tuning
Yoann Launay, Parameswaran Kamalaruban, Tom Kempton +2
Vision-language models have displayed remarkable capabilities in multi-modal understanding and are increasingly used in critical applications where economic and practical deploymen…
MINT: A Universal Zero-Shot Predictor for Transaction Data
Parameswaran Kamalaruban, Viktor Drobnyi, Maeve Madigan +3
Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalization. To improve the predictive a…
Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback
Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban +2
We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset of…
DMAP: A Distribution Map for Text
Tom Kempton, Julia Rozanova, Parameswaran Kamalaruban +5
Large Language Models (LLMs) are a powerful tool for statistical text analysis, with derived sequences of next-token probability distributions offering a wealth of information. Ext…
Emergent Bias and Fairness in Multi-Agent Decision Systems
Maeve Madigan, Parameswaran Kamalaruban, Glenn Moynihan +3
Multi-agent systems have demonstrated the ability to improve performance on a variety of predictive tasks by leveraging collaborative decision making. However, the lack of effectiv…
Inference-Time Personalized Alignment with a Few User Preference Queries
Victor-Alexandru Pădurean, Parameswaran Kamalaruban, Nachiket Kotalwar +2
We study the problem of aligning a generative model's response with a user's preferences. Recent works have proposed several different formulations for personalized alignment; howe…
Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla
Training agents to operate under strict constraints during deployment, such as limited resource budgets or stringent safety requirements, presents significant challenges, especiall…
Policy Teaching via Data Poisoning in Learning from Human Preferences
Andi Nika, Jonathan Nöther, Debmalya Mandal +3
We study data poisoning attacks in learning from human preferences. More specifically, we consider the problem of teaching/enforcing a target policy by synthesizing pre…
Fairness-Aware Low-Rank Representation Fine-Tuning
Parameswaran Kamalaruban, Mark Anderson, Stuart Burrell +3
Pre-trained foundation models can be efficiently adapted for specific tasks using Low-Rank Adaptation (LoRA), but the fairness properties of these adapted classifiers remain undere…
Evaluating Fairness in Transaction Fraud Models: Fairness Metrics, Bias Audits, and Challenges
Parameswaran Kamalaruban, Yulu Pi, Stuart Burrell +4
Ensuring fairness in transaction fraud detection models is vital due to the potential harms and legal implications of biased decision-making. Despite extensive research on algorith…
Adversarially Robust Decision Transformer
Xiaohang Tang, Afonso Marques, Parameswaran Kamalaruban +1
Decision Transformer (DT), as one of the representative Reinforcement Learning via Supervised Learning (RvS) methods, has achieved strong performance in offline learning tasks by l…
Proximal Curriculum with Task Correlations for Deep Reinforcement Learning
Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla
Curriculum design for reinforcement learning (RL) can speed up an agent's learning process and help it learn to perform well on complex tasks. However, existing techniques typicall…
Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban +3
In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedba…
Informativeness of Reward Functions in Reinforcement Learning
Rati Devidze, Parameswaran Kamalaruban, Adish Singla
Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing…
Corruption Robust Offline Reinforcement Learning with Human Feedback
Debmalya Mandal, Andi Nika, Parameswaran Kamalaruban +2
We study data corruption robustness for reinforcement learning with human feedback (RLHF) in an offline setting. Given an offline dataset of pairs of trajectories along with feedba…
Proximal Curriculum for Reinforcement Learning Agents
Georgios Tzannetos, Bárbara Gomes Ribeiro, Parameswaran Kamalaruban +1
We consider the problem of curriculum design for reinforcement learning (RL) agents in contextual multi-task settings. Existing techniques on automatic curriculum design typically…
Learning Personalized Decision Support Policies
Umang Bhatt, Valerie Chen, Katherine M. Collins +4
Individual human decision-makers may benefit from different forms of support to improve decision outcomes, but when each form of support will yield better outcomes? In this work, w…
Robust Learning from Observation with Model Misspecification
Luca Viano, Yu-Ting Huang, Parameswaran Kamalaruban +3
Imitation learning (IL) is a popular paradigm for training policies in robotic systems when specifying the reward function is difficult. However, despite the success of IL algorith…
Curriculum Design for Teaching via Demonstrations: Theory and Applications
Gaurav Yengera, Rati Devidze, Parameswaran Kamalaruban +1
We consider the problem of teaching via demonstrations in sequential decision-making settings. In particular, we study how to design a personalized curriculum over demonstrations t…
Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
Luca Viano, Yu-Ting Huang, Parameswaran Kamalaruban +2
We study the inverse reinforcement learning (IRL) problem under a transition dynamics mismatch between the expert and the learner. Specifically, we consider the Maximum Causal Entr…
Interaction-limited Inverse Reinforcement Learning
Martin Troussard, Emmanuel Pignat, Parameswaran Kamalaruban +2
This paper proposes an inverse reinforcement learning (IRL) framework to accelerate learning when the learner-teacher \textit{interaction} is \textit{limited} during training. Our…
Environment Shaping in Reinforcement Learning using State Abstraction
Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher +1
One of the central challenges faced by a reinforcement learning (RL) agent is to effectively learn a (near-)optimal policy in environments with large state spaces having sparse and…
Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
Parameswaran Kamalaruban, Yu-Ting Huang, Ya-Ping Hsieh +3
We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynam…