Search Results for author: Keerthiram Murugesan

Found 45 papers, 12 papers with code

Context Attribution with Multi-Armed Bandit Optimization

no code implementations24 Jun 2025 Deng Pan, Keerthiram Murugesan, Nuno Moniz, Nitesh Chawla

Each context segment is treated as a bandit arm, and we employ Combinatorial Thompson Sampling (CTS) to efficiently explore the exponentially large space of context subsets under a limited query budget.

Thompson Sampling

AutoData: A Multi-Agent System for Open Web Data Collection

1 code implementation21 May 2025 Tianyi Ma, Yiyue Qian, Zheyuan Zhang, Zehong Wang, Xiaoye Qian, Feifan Bai, Yifan Ding, Xuwei Luo, Shinan Zhang, Keerthiram Murugesan, Chuxu Zhang, Yanfang Ye

To address these challenges, we propose AutoData, a novel multi-agent system for Automated web Data collection, that requires minimal human intervention, i. e., only necessitating a natural language instruction specifying the desired dataset.

Large Language Model

EfficientLLM: Efficiency in Large Language Models

no code implementations20 May 2025 Zhengqing Yuan, Weixiang Sun, Yixin Liu, Huichi Zhou, Rong Zhou, Yiyang Li, Zheyuan Zhang, Wei Song, Yue Huang, Haolong Jia, Keerthiram Murugesan, Yu Wang, Lifang He, Jianfeng Gao, Lichao Sun, Yanfang Ye

Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs.

Mixture-of-Experts Quantization

PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks

no code implementations8 Apr 2025 Huzaifa Arif, Keerthiram Murugesan, Payel Das, Alex Gittens, Pin-Yu Chen

By formulating inference-time data leakage as a constrained optimization problem, we propose a novel backward feature inversion method, \textbf{PEEL}, which can effectively recover block-wise input features from the intermediate output of residual NNs.

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents

no code implementations22 Feb 2025 Ivoline Ngong, Swanand Kadhe, Hao Wang, Keerthiram Murugesan, Justin D. Weisz, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy

It aims to minimize privacy risks by ensuring that users (sender) disclose only information that is both relevant and necessary for achieving their intended goals when interacting with LLMs (untrusted receivers).

NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning

no code implementations20 Dec 2024 Zheyuan Zhang, Yiyang Li, Nhi Ha Lan Le, Zehong Wang, Tianyi Ma, Vincent Galassi, Keerthiram Murugesan, Nuno Moniz, Werner Geyer, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye

On the other hand, while large language models (LLMs), a popular solution for this task, demonstrate strong reasoning abilities, they struggle with the domain-specific complexities of personalized healthy dietary reasoning, and existing benchmarks fail to capture these challenges.

Graph Question Answering Nutrition +1

Combinatorial Multi-armed Bandits: Arm Selection via Group Testing

no code implementations14 Oct 2024 Arpan Mukherjee, Shashanka Ubaru, Keerthiram Murugesan, Karthikeyan Shanmugam, Ali Tajer

Under a general separability assumption on the reward function, the proposed algorithm reduces the complexity of the super-arm-selection oracle to be logarithmic in the number of base arms while achieving the same regret order as the state-of-the-art algorithms that use exact oracles.

parameter estimation Thompson Sampling

Towards Aligning Language Models with Textual Feedback

1 code implementation24 Jul 2024 Saüc Abadal Lloret, Shehzaad Dhuliawala, Keerthiram Murugesan, Mrinmaya Sachan

We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text.

Language Modeling Language Modelling +1

CTBench: A Comprehensive Benchmark for Evaluating Language Model Capabilities in Clinical Trial Design

1 code implementation25 Jun 2024 Nafis Neehal, Bowen Wang, Shayom Debopadhaya, Soham Dan, Keerthiram Murugesan, Vibha Anand, Kristin P. Bennett

Given study-specific metadata, CTBench evaluates AI models' ability to determine the baseline features of a clinical trial (CT), which include demographic and relevant features collected at the trial's start from all participants.

Language Modeling Language Modelling +1

STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models

1 code implementation9 Jun 2024 Shreyas Basavatia, Keerthiram Murugesan, Shivam Ratnakar

In this work, we introduce an interactive environment for self-supervised RL, STARLING, for text-based games that bootstraps the text-based RL agents with automatically generated games (based on the seed set of game ideas) to boost the performance and generalization capabilities to reach a goal of the target environment.

Reinforcement Learning (RL) text-based games

Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions

no code implementations30 May 2024 Hyo Jin Do, Rachel Ostrand, Justin D. Weisz, Casey Dugan, Prasanna Sattigeri, Dennis Wei, Keerthiram Murugesan, Werner Geyer

To address this issue, we conducted a scenario-based study (N=104) to systematically compare the impact of various design strategies for communicating factuality and source attribution on participants' ratings of trust, preferences, and ease in validating response accuracy.

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning

no code implementations24 May 2024 Shuai Zhang, Heshan Devaka Fernando, Miao Liu, Keerthiram Murugesan, Songtao Lu, Pin-Yu Chen, Tianyi Chen, Meng Wang

This paper studies the transfer reinforcement learning (RL) problem where multiple RL problems have different reward functions but share the same underlying transition dynamics.

Deep Reinforcement Learning Q-Learning +2

On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning

no code implementations15 Apr 2024 Mauricio Gruppi, Soham Dan, Keerthiram Murugesan, Subhajit Chaudhury

Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL).

reinforcement-learning Reinforcement Learning

Language Guided Exploration for RL Agents in Text Environments

no code implementations5 Mar 2024 Hitesh Golchha, Sahil Yerawar, Dhruvesh Patel, Soham Dan, Keerthiram Murugesan

Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents.

Decision Making Language Modeling +4

Value-based Fast and Slow AI Nudging

no code implementations14 Jul 2023 Marianna B. Ganapini, Francesco Fabiano, Lior Horesh, Andrea Loreggia, Nicholas Mattei, Keerthiram Murugesan, Vishal Pallagani, Francesca Rossi, Biplav Srivastava, Brent Venable

Values that are relevant to a specific decision scenario are used to decide when and how to use each of these nudging modalities.

Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning

1 code implementation5 Jul 2023 Subhajit Chaudhury, Sarathkrishna Swaminathan, Daiki Kimura, Prithviraj Sen, Keerthiram Murugesan, Rosario Uceda-Sosa, Michiaki Tatsubori, Achille Fokoue, Pavan Kapanipathi, Asim Munawar, Alexander Gray

Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games.

Deep Reinforcement Learning reinforcement-learning +1

Plansformer: Generating Symbolic Plans using Transformers

no code implementations16 Dec 2022 Vishal Pallagani, Bharath Muppasani, Keerthiram Murugesan, Francesca Rossi, Lior Horesh, Biplav Srivastava, Francesco Fabiano, Andrea Loreggia

Large Language Models (LLMs) have been the subject of active research, significantly advancing the field of Natural Language Processing (NLP).

Question Answering Text Generation +2

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach

4 code implementations23 Oct 2022 Heshan Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen

Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them.

Fairness Inductive Bias +1

Targeted Advertising on Social Networks Using Online Variational Tensor Regression

no code implementations22 Aug 2022 Tsuyoshi Idé, Keerthiram Murugesan, Djallel Bouneffouf, Naoki Abe

The proposed framework is designed to accommodate any number of feature vectors in the form of multi-mode tensor, thereby enabling to capture the heterogeneity that may exist over user preferences, products, and campaign strategies in a unified manner.

Marketing regression

Auto-Transfer: Learning to Route Transferrable Representations

1 code implementation2 Feb 2022 Keerthiram Murugesan, Vijay Sadashivaiah, Ronny Luss, Karthikeyan Shanmugam, Pin-Yu Chen, Amit Dhurandhar

Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications.

Transfer Learning

Case-based Reasoning for Better Generalization in Textual Reinforcement Learning

no code implementations ICLR 2022 Mattia Atzeni, Shehzaad Dhuliawala, Keerthiram Murugesan, Mrinmaya Sachan

Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency.

Deep Reinforcement Learning Out-of-Distribution Generalization +3

Auto-Transfer: Learning to Route Transferable Representations

no code implementations ICLR 2022 Keerthiram Murugesan, Vijay Sadashivaiah, Ronny Luss, Karthikeyan Shanmugam, Pin-Yu Chen, Amit Dhurandhar

Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labelled data can be difficult to obtain in many applications.

Transfer Learning

Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents

no code implementations9 Jun 2021 Keerthiram Murugesan, Subhajit Chaudhury, Kartik Talamadupula

This improves the agent's overall understanding of the game 'scene' and objects' relationships to the world around them, and the variety of visual representations on offer allow the agent to generate a better generalization of a relationship.

reinforcement-learning Reinforcement Learning (RL) +2

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Approaches

no code implementations12 Jul 2020 Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Pushkar Shukla, Sadhana Kumaravel, Gerald Tesauro, Kartik Talamadupula, Mrinmaya Sachan, Murray Campbell

We introduce a number of RL agents that combine the sequential context with a dynamic graph representation of their beliefs of the world and commonsense knowledge from ConceptNet in different ways.

Decision Making Reinforcement Learning (RL) +2

Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge

no code implementations2 May 2020 Keerthiram Murugesan, Mattia Atzeni, Pushkar Shukla, Mrinmaya Sachan, Pavan Kapanipathi, Kartik Talamadupula

In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments.

reinforcement-learning Reinforcement Learning +1

Lifelong Learning with Output Kernels

no code implementations ICLR 2018 Keerthiram Murugesan, Jaime Carbonell

Lifelong learning poses considerable challenges in terms of effectiveness (minimizing prediction errors for all tasks) and overall computational tractability for real-time performance.

Lifelong learning

Active Learning from Peers

no code implementations NeurIPS 2017 Keerthiram Murugesan, Jaime Carbonell

This paper addresses the challenge of learning from peers in an online multitask setting.

Active Learning

Co-Clustering for Multitask Learning

no code implementations3 Mar 2017 Keerthiram Murugesan, Jaime Carbonell, Yiming Yang

This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters.

Clustering

Self-Paced Multitask Learning with Shared Knowledge

no code implementations2 Mar 2017 Keerthiram Murugesan, Jaime Carbonell

This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning.

Adaptive Smoothed Online Multi-Task Learning

no code implementations NeurIPS 2016 Keerthiram Murugesan, Hanxiao Liu, Jaime Carbonell, Yiming Yang

This paper addresses the challenge of jointly learning both the per-task model parameters and the inter-task relationships in a multi-task online learning setting.

Multi-Task Learning

Multi-Task Multiple Kernel Relationship Learning

no code implementations10 Nov 2016 Keerthiram Murugesan, Jaime Carbonell

The problem is formulated as a regularization-based approach called \textit{Multi-Task Multiple Kernel Relationship Learning} (\textit{MK-MTRL}), which models the task relationship matrix from the weights learned from latent feature spaces of task-specific base kernels.

Cannot find the paper you are looking for? You can Submit a new open access paper.