52 citations · 153 across the 67 of their papers we have counts for
13 papers · 1 filter
Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games
Arjun Vaithilingam Sudhakar, Prasanna Parthasarathi, Janarthanan Rajendran +1
Large Language Models (LLMs) have demonstrated superior performance in language understanding benchmarks. CALM, a popular approach, leverages linguistic priors of LLMs -- GPT-2 --…
Self-Influence Guided Data Reweighting for Language Model Pre-training
Megh Thakkar, Tolga Bolukbasi, Sriram Ganapathy +3
Language Models (LMs) pre-trained with self-supervision on large text corpora have become the default starting point for developing models for various NLP tasks. Once the pre-train…
EpiK-Eval: Evaluation for Language Models as Epistemic Models
Gabriele Prato, Jerry Huang, Prasannna Parthasarathi +2
In the age of artificial intelligence, the role of large language models (LLMs) is becoming increasingly central. Despite their growing prevalence, their capacity to consolidate kn…
Faithfulness Measurable Masked Language Models
Andreas Madsen, Siva Reddy, Sarath Chandar
A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong…
Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi
Hadi Nekoei, Xutong Zhao, Janarthanan Rajendran +2
Cooperative Multi-agent Reinforcement Learning (MARL) algorithms with Zero-Shot Coordination (ZSC) have gained significant attention in recent years. ZSC refers to the ability of a…
Lookbehind-SAM: k steps back, 1 step forward
Gonçalo Mordido, Pranshu Malviya, Aristide Baratin +1
Sharpness-aware minimization (SAM) methods have gained increasing popularity by formulating the problem of minimizing both loss value and loss sharpness as a minimax objective. In…
Promoting Exploration in Memory-Augmented Adam using Critical Momenta
Pranshu Malviya, Gonçalo Mordido, Aristide Baratin +5
Adaptive gradient-based optimizers, notably Adam, have left their mark in training large-scale deep learning models, offering fast convergence and robustness to hyperparameter sett…
Thompson sampling for improved exploration in GFlowNets
Jarrid Rector-Brooks, Kanika Madan, Moksh Jain +5
Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-maki…
Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models
Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi +1
While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts of knowledge, it remains unclear how much of this parametric knowledge is actually usable in…
Should We Attend More or Less? Modulating Attention for Fairness
Abdelrahman Zayed, Goncalo Mordido, Samira Shabanian +1
The advances in natural language processing (NLP) pose both opportunities and challenges. While recent progress enables the development of high-performing models for a variety of t…
On the Costs and Benefits of Adopting Lifelong Learning for Software Analytics -- Empirical Study on Brown Build and Risk Prediction
Doriane Olewicki, Sarra Habchi, Mathieu Nayrolles +3
Nowadays, software analytics tools using machine learning (ML) models to, for example, predict the risk of a code change are well established. However, as the goals of a project sh…
Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning
Xutong Zhao, Yangchen Pan, Chenjun Xiao +2
Efficient exploration is critical in cooperative deep Multi-Agent Reinforcement Learning (MARL). In this work, we propose an exploration method that effectively encourages cooperat…
Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning
Hadi Nekoei, Akilesh Badrinaaraayanan, Amit Sinha +4
Decentralized cooperative multi-agent deep reinforcement learning (MARL) can be a versatile learning framework, particularly in scenarios where centralized training is either not p…