Author name cluster

Sayan Ghosh

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICLR Conference 2025 Conference Paper

Enhancing Language Model Agents using Diversity of Thoughts

Vijay Lingam
Behrooz Omidvar-Tehrani
Sujay Sanghavi
Gaurav Gupta
Sayan Ghosh
Linbo Liu
Jun Huan
Anoop Deoras

A popular approach to building agents using Language Models (LMs) involves iteratively prompting the LM, reflecting on its outputs, and updating the input prompts until the desired task is achieved. However, our analysis reveals two key shortcomings in the existing methods: $(i)$ limited exploration of the decision space due to repetitive reflections, which result in redundant inputs, and $(ii)$ an inability to leverage insights from previously solved tasks. To address these issues, we introduce DoT (Diversity of Thoughts), a novel framework that a) explicitly reduces redundant reflections to enhance decision-space exploration, and b) incorporates a task-agnostic memory component to enable knowledge retrieval from previously solved tasks—unlike current approaches that operate in isolation for each task. Through extensive experiments on a suite of programming benchmarks (HumanEval, MBPP, and LeetCodeHardGym) using a variety of LMs, DoT demonstrates up to a $\textbf{10}$% improvement in Pass@1 while maintaining cost-effectiveness. Furthermore, DoT is modular by design. For instance, when the diverse reflection module of DoT is integrated with existing methods like Tree of Thoughts (ToT), we observe a significant $\textbf{13}$% improvement on Game of 24 (one of the main benchmarks of ToT), highlighting the broad applicability and impact of our contributions across various reasoning tasks.

Details

EAAI Journal 2025 Journal Article

Interpretable multi-source data fusion through Latent Variable Gaussian Process

Sandipp Krishnan Ravi
Yigitcan Comlek
Arjun Pathak
Vipul Gupta
Rajnikant Umretiya
Andrew Hoffman
Ghanshyam Pilania
Piyush Pandita

With the advent of artificial intelligence and machine learning, various domains of science and engineering communities have leveraged data-driven surrogates to model complex systems through fusing numerous sources of information (data) from published papers, patents, open repositories, or other available resources. However, very little attention has been paid to the differences in quality and comprehensiveness of the known and unknown underlying physical parameters of the information sources, which could have downstream implications during system optimization. Towards resolving this issue, an interpretable multi-source data fusion framework based on Latent Variable Gaussian Process (LVGP) model is proposed. The individual data sources are first labeled as categorical variables and then mapped into a physically meaningful latent space, enabling the development of a source-aware data fusion model. Additionally, a dissimilarity metric based on the learned latent variables of the LVGP is introduced to study and understand the differences between the data sources. The proposed approach is demonstrated on and analyzed through two mathematical and two materials engineering case studies. From the case studies, it is observed that the proposed multi-source data fusion framework provides more accurate predictions for sparse data scenarios compared to single-source or source-unaware data fusion models.

Details DOI

TMLR Journal 2023 Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava
Abhinav Rastogi
Abhishek Rao
Abu Awal Md Shoeb
Abubakar Abid
Adam Fisch
Adam R. Brown
Adam Santoro

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG- bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood develop- ment, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google- internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

PDF Details

AAMAS Conference 2018 Conference Paper

NADiA - Towards Neural Network Driven Virtual Human Conversation Agents

Jason Wu
Sayan Ghosh
Mathieu Chollet
Steven Ly
Sharon Mozgai
Stefan Scherer

Advances in artificial intelligence and machine learning - in particular neural networks - have given rise to a new generation of virtual assistants and chatbots. Within this work, we describe the motivation and architecture of NADiA - Neurally Animated Dialog Agent which leverages both the user’s verbal input and facial expressions for multi-modal conversation. NADiA combines a neural language model that generates conversational responses, a convolutional neural network for facial expression analysis, and virtual human technology that is deployed on a mobile phone.

PDF