Search Results for author: Soham Dan

Found 28 papers, 5 papers with code

Generalized Planning in PDDL Domains with Pretrained Large Language Models

1 code implementation18 May 2023 Tom Silver, Soham Dan, Kavitha Srinivas, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Michael Katz

We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain.

Compositional Program Generation for Few-Shot Systematic Generalization

1 code implementation28 Sep 2023 Tim Klinger, Luke Liu, Soham Dan, Maxwell Crouse, Parikshit Ram, Alexander Gray

Compositional generalization is a key ability of humans that enables us to learn new concepts from only a handful examples.

Systematic Generalization

AppTechMiner: Mining Applications and Techniques from Scientific Articles

no code implementations10 Sep 2017 Mayank Singh, Soham Dan, Sanyam Agarwal, Pawan Goyal, Animesh Mukherjee

We also categorize individual research articles based on their application areas and the techniques proposed/improved in the article.

Information Retrieval Retrieval

Which techniques does your application use?: An information extraction framework for scientific articles

no code implementations23 Aug 2016 Soham Dan, Sanyam Agarwal, Mayank Singh, Pawan Goyal, Animesh Mukherjee

Every field of research consists of multiple application areas with various techniques routinely used to solve problems in these wide range of application areas.

Language Modelling

Variance Reduced Stochastic Proximal Algorithm for AUC Maximization

no code implementations8 Nov 2019 Soham Dan, Dushyant Sahoo

To combat this issue, several variance reduced methods have been proposed with faster convergence guarantees than vanilla stochastic gradient descent.

Learning from Noisy Similar and Dissimilar Data

no code implementations3 Feb 2020 Soham Dan, Han Bao, Masashi Sugiyama

We perform a detailed investigation of this problem under two realistic noise models and propose two algorithms to learn from noisy S-D data.

From Spatial Relations to Spatial Configurations

no code implementations LREC 2020 Soham Dan, Parisa Kordjamshidi, Julia Bonn, Archna Bhatia, Jon Cai, Martha Palmer, Dan Roth

To exhibit the applicability of our representation scheme, we annotate text taken from diverse datasets and show how we extend the capabilities of existing spatial representation languages with the fine-grained decomposition of semantics and blend it seamlessly with AMRs of sentences and discourse representations as a whole.

Natural Language Understanding

Understanding Spatial Relations through Multiple Modalities

no code implementations LREC 2020 Soham Dan, Hangfeng He, Dan Roth

Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general.

Common Sense Reasoning Implicit Relations

Goodness-of-Fit Tests for Inhomogeneous Random Graphs

no code implementations ICML 2020 Soham Dan, Bhaswar B. Bhattacharya

Hypothesis testing of random networks is an emerging area of modern research, especially in the high-dimensional regime, where the number of samples is smaller or comparable to the size of the graph.

Two-sample testing

Generalization in Instruction Following Systems

no code implementations NAACL 2021 Soham Dan, Michael Zhou, Dan Roth

Understanding and executing natural language instructions in a grounded domain is one of the hallmarks of artificial intelligence.

Data Augmentation Instruction Following

A Locally Linear Procedure for Word Translation

no code implementations COLING 2020 Soham Dan, Hagai Taitelbaum, Jacob Goldberger

We propose a natural extension of the PA algorithm that uses multiple orthogonal translation matrices to model the mapping and derive an algorithm to learn these multiple matrices.

Translation Word Embeddings +2

Dynamics of Local Elasticity During Training of Neural Nets

1 code implementation1 Nov 2021 Soham Dan, Anirbit Mukherjee, Avirup Das, Phanideep Gampa

On various state-of-the-art neural network training on SVHN, CIFAR-10 and CIFAR-100 we demonstrate how our new proposal of $S_{\rm rel}$, as opposed to the original definition, much more sharply detects the property of the weight updates preferring to make prediction changes within the same class as the sampled data.

regression

Few-Shot Novel Concept Learning for Semantic Parsing

no code implementations Findings (EMNLP) 2021 Soham Dan, Osbert Bastani, Dan Roth

This way the concept learning problem is naturally a program synthesis problem and our algorithm learns from a few examples to synthesize a program representing the novel concept.

Novel Concepts Program Synthesis +1

Compositional Data and Task Augmentation for Instruction Following

no code implementations Findings (EMNLP) 2021 Soham Dan, Xinran Han, Dan Roth

Executing natural language instructions in a physically grounded domain requires a model that understands both spatial concepts such as “left of” and “above”, and the compositional language used to identify landmarks and articulate instructions relative to them.

Instruction Following

On the Effects of Transformer Size on In- and Out-of-Domain Calibration

no code implementations Findings (EMNLP) 2021 Soham Dan, Dan Roth

To reduce the cost of training such large models, prior work has developed smaller, more compact models which achieves a significant speedup in training time while maintaining competitive accuracy to the original model on downstream tasks.

Understanding Robust Generalization in Learning Regular Languages

no code implementations20 Feb 2022 Soham Dan, Osbert Bastani, Dan Roth

Currently, deep neural networks struggle to generalize robustly to such shifts in the data distribution.

One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits

no code implementations26 Oct 2022 Pierre Gaillard, Aadirupa Saha, Soham Dan

We address the problem of \emph{`Internal Regret'} in \emph{Sleeping Bandits} in the fully adversarial setup, as well as draw connections between different existing notions of sleeping regrets in the multiarmed bandits (MAB) literature and consequently analyze the implications: Our first contribution is to propose the new notion of \emph{Internal Regret} for sleeping MAB.

In and Out-of-Domain Text Adversarial Robustness via Label Smoothing

no code implementations20 Dec 2022 Yahan Yang, Soham Dan, Dan Roth, Insup Lee

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions).

Adversarial Robustness

Formally Specifying the High-Level Behavior of LLM-Based Agents

no code implementations12 Oct 2023 Maxwell Crouse, Ibrahim Abdelaziz, Ramon Astudillo, Kinjal Basu, Soham Dan, Sadhana Kumaravel, Achille Fokoue, Pavan Kapanipathi, Salim Roukos, Luis Lastras

We demonstrate how the proposed framework can be used to implement recent LLM-based agents (e. g., ReACT), and show how the flexibility of our approach can be leveraged to define a new agent with more complex behavior, the Plan-Act-Summarize-Solve (PASS) agent.

Question Answering

Understanding Calibration for Multilingual Question Answering Models

no code implementations15 Nov 2023 Yahan Yang, Soham Dan, Dan Roth, Insup Lee

We also conduct a number of ablation experiments to study the effect of model size on calibration and how multilingual models compare with their monolingual counterparts for diverse tasks and languages.

Cross-Lingual Transfer Data Augmentation +2

On the generalization capacity of neural networks during generic multimodal reasoning

1 code implementation26 Jan 2024 Takuya Ito, Soham Dan, Mattia Rigotti, James Kozloski, Murray Campbell

On the other hand, neither of these architectural features led to productive generalization, suggesting fundamental limitations of existing architectures for specific types of multimodal generalization.

Multimodal Reasoning Systematic Generalization

API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs

no code implementations23 Feb 2024 Kinjal Basu, Ibrahim Abdelaziz, Subhajit Chaudhury, Soham Dan, Maxwell Crouse, Asim Munawar, Sadhana Kumaravel, Vinod Muthusamy, Pavan Kapanipathi, Luis A. Lastras

There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks.

Benchmarking slot-filling +2

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 Modelling +2

Larimar: Large Language Models with Episodic Memory Control

no code implementations18 Mar 2024 Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aurélie Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jiří, Navrátil, Soham Dan, Pin-Yu Chen

Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today.

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