papers

Publications (77)

cs.CL2021

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

Dinesh Raghu, Shantanu Agarwal, Sachindra Joshi +1

We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their…

cond-mat.mtrl-sci2025

Foundational Large Language Models for Materials Research

Vaibhav Mishra, Somaditya Singh, Dhruv Ahlawat +7

Materials discovery and development are critical for addressing global challenges. Yet, the exponential growth in materials science literature comprising vast amounts of textual da…

cs.SI2020

Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols

Prachi Jain, Sushant Rathi, Mausam +1

Temporal knowledge bases associate relational (s,r,o) triples with a set of times (or a single time instant) when the relation is valid. While time-agnostic KB completion (KBC) has…

cs.LG2023

Towards Fair and Calibrated Models

Anand Brahmbhatt, Vipul Rathore, Mausam +1

Recent literature has seen a significant focus on building machine learning models with specific properties such as fairness, i.e., being non-biased with respect to a given set of…

cs.CL2023

CoRE-CoG: Conversational Recommendation of Entities using Constrained Generation

Harshvardhan Srivastava, Kanav Pruthi, Soumen Chakrabarti +1

End-to-end conversational recommendation systems (CRS) generate responses by leveraging both dialog history and a knowledge base (KB). A CRS mainly faces three key challenges: (1)…

cs.CV2023

DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting

Aayush Kumar Tyagi, Chirag Mohapatra, Prasenjit Das +4

Multi-class cell detection and counting is an essential task for many pathological diagnoses. Manual counting is tedious and often leads to inter-observer variations among patholog…

cs.CL2026

The Percept-V Challenge: Can Multimodal LLMs Crack Simple Perception Problems?

Samrajnee Ghosh, Naman Agarwal, Hemanshu Garg +3

Cognitive science research treats visual perception, the ability to understand and make sense of a visual input, as one of the early developmental signs of intelligence. Its TVPS-4…

cs.CL2024

What Can Natural Language Processing Do for Peer Review?

Ilia Kuznetsov, Osama Mohammed Afzal, Koen Dercksen +21

The number of scientific articles produced every year is growing rapidly. Providing quality control over them is crucial for scientists and, ultimately, for the public good. In mod…

cs.CL2024

DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion

Ananjan Nandi, Navdeep Kaur, Parag Singla +1

We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connect…

cs.CL2024

Reconstructing Materials Tetrahedron: Challenges in Materials Information Extraction

Kausik Hira, Mohd Zaki, Dhruvil Sheth +2

The discovery of new materials has a documented history of propelling human progress for centuries and more. The behaviour of a material is a function of its composition, structure…

cs.LG2021

Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces

Yatin Nandwani, Deepanshu Jindal, Mausam +1

Recent research has proposed neural architectures for solving combinatorial problems in structured output spaces. In many such problems, there may exist multiple solutions for a gi…

cs.CL2023

Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs

Pranjal Aggarwal, Aman Madaan, Yiming Yang +1

A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution…

cs.CL2023

ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters

Vipul Rathore, Rajdeep Dhingra, Parag Singla +1

We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a si…

cs.IR2026

MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables

Kausik Hira, Mohd Zaki, Mausam +1

Scientific progress increasingly depends on synthesizing knowledge across vast literature, yet most experimental data remains trapped in semi-structured formats that resist systema…

cs.CV2017

Coarse-to-Fine Lifted MAP Inference in Computer Vision

Haroun Habeeb, Ankit Anand, Mausam +1

There is a vast body of theoretical research on lifted inference in probabilistic graphical models (PGMs). However, few demonstrations exist where lifting is applied in conjunction…

cs.CL2021

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

Dinesh Raghu, Atishya Jain, Mausam +1

End-to-End task-oriented dialogue systems generate responses based on dialog history and an accompanying knowledge base (KB). Inferring those KB entities that are most relevant for…

cs.CL2021

DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction

Abhyuday Bhartiya, Kartikeya Badola, Mausam

Distant supervision (DS) is a well established technique for creating large-scale datasets for relation extraction (RE) without using human annotations. However, research in DS-RE…

cs.CL2020

OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction

Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal +2

A recent state-of-the-art neural open information extraction (OpenIE) system generates extractions iteratively, requiring repeated encoding of partial outputs. This comes at a sign…

cs.CL2025

AutoMix: Automatically Mixing Language Models

Pranjal Aggarwal, Aman Madaan, Ankit Anand +10

Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively le…

cs.AI2018

Transfer of Deep Reactive Policies for MDP Planning

Aniket Bajpai, Sankalp Garg, Mausam

Domain-independent probabilistic planners input an MDP description in a factored representation language such as PPDDL or RDDL, and exploit the specifics of the representation for…

cs.CL2024

RetinaQA: A Robust Knowledge Base Question Answering Model for both Answerable and Unanswerable Questions

Prayushi Faldu, Indrajit Bhattacharya, Mausam

An essential requirement for a real-world Knowledge Base Question Answering (KBQA) system is the ability to detect the answerability of questions when generating logical forms. How…

cs.LG2022

Knowledge Base Completion: Baseline strikes back (Again)

Prachi Jain, Sushant Rathi, Mausam +1

Knowledge Base Completion (KBC) has been a very active area lately. Several recent KBCpapers propose architectural changes, new training methods, or even new formulations. KBC syst…

cs.DB2025

STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databases

Mounica Maddela, Lingjue Xie, Daniel Preotiuc-Pietro +1

Semantic parsing methods for converting text to SQL queries enable question answering over structured data and can greatly benefit analysts who routinely perform complex analytics…

cs.CV2025

BoxCell: Leveraging SAM for Cell Segmentation with Box Supervision

Aayush Kumar Tyagi, Vaibhav Mishra, Prathosh A. P. +1

Cell segmentation in histopathological images is vital for diagnosis, and treatment of several diseases. Annotating data is tedious, and requires medical expertise, making it diffi…

cs.AI2017

Joint Matrix-Tensor Factorization for Knowledge Base Inference

Prachi Jain, Shikhar Murty, Mausam +1

While several matrix factorization (MF) and tensor factorization (TF) models have been proposed for knowledge base (KB) inference, they have rarely been compared across various dat…

cs.LG2022

Neural Models for Output-Space Invariance in Combinatorial Problems

Yatin Nandwani, Vidit Jain, Mausam +1

Recently many neural models have been proposed to solve combinatorial puzzles by implicitly learning underlying constraints using their solved instances, such as sudoku or graph co…

cs.AI2016

Contextual Symmetries in Probabilistic Graphical Models

Ankit Anand, Aditya Grover, Mausam +1

An important approach for efficient inference in probabilistic graphical models exploits symmetries among objects in the domain. Symmetric variables (states) are collapsed into met…

cs.CL2023

MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models

Mohd Zaki, Jayadeva, Mausam +1

Information extraction and textual comprehension from materials literature are vital for developing an exhaustive knowledge base that enables accelerated materials discovery. Langu…

cs.CL2024

Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems

Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu +1

End-to-end Task-Oriented Dialog (TOD) systems typically require extensive training datasets to perform well. In contrast, large language model (LLM) based TOD systems can excel eve…

cs.AI2017

Non-Count Symmetries in Boolean & Multi-Valued Prob. Graphical Models

Ankit Anand, Ritesh Noothigattu, Parag Singla +1

Lifted inference algorithms commonly exploit symmetries in a probabilistic graphical model (PGM) for efficient inference. However, existing algorithms for Boolean-valued domains ca…

cs.AI2020

Joint Spatio-Textual Reasoning for Answering Tourism Questions

Danish Contractor, Shashank Goel, Mausam +1

Our goal is to answer real-world tourism questions that seek Points-of-Interest (POI) recommendations. Such questions express various kinds of spatial and non-spatial constraints,…

cs.RO2022

GoalNet: Inferring Conjunctive Goal Predicates from Human Plan Demonstrations for Robot Instruction Following

Shreya Sharma, Jigyasa Gupta, Shreshth Tuli +2

Our goal is to enable a robot to learn how to sequence its actions to perform tasks specified as natural language instructions, given successful demonstrations from a human partner…

cs.CV2021

Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation

Prashant Pandey, Ajey Pai, Nisarg Bhatt +4

Contrastive Learning (CL) is a recent representation learning approach, which encourages inter-class separability and intra-class compactness in learned image representations. Sinc…

cs.AI2012

Crowdsourcing Control: Moving Beyond Multiple Choice

Christopher H. Lin, Mausam, Daniel Weld

To ensure quality results from crowdsourced tasks, requesters often aggregate worker responses and use one of a plethora of strategies to infer the correct answer from the set of n…

cs.CL2023

mOKB6: A Multilingual Open Knowledge Base Completion Benchmark

Shubham Mittal, Keshav Kolluru, Soumen Chakrabarti +1

Automated completion of open knowledge bases (Open KBs), which are constructed from triples of the form (subject phrase, relation phrase, object phrase), obtained via open informat…

cs.LG2019

Disentangling Language and Knowledge in Task-Oriented Dialogs

Dinesh Raghu, Nikhil Gupta, Mausam

The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these…

cs.CL2024

A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification

D. Subhalingam, Keshav Kolluru, Mausam +1

In the e-commerce domain, the accurate extraction of attribute-value pairs (e.g., Brand: Apple) from product titles and user search queries is crucial for enhancing search and reco…

cs.CL2023

Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models

Daman Arora, Himanshu Gaurav Singh, Mausam

The performance of large language models (LLMs) on existing reasoning benchmarks has significantly improved over the past years. In response, we present JEEBench, a considerably mo…

cs.CL2023

DKAF: KB Arbitration for Learning Task-Oriented Dialog Systems with Dialog-KB Inconsistencies

Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu +1

Task-oriented dialog (TOD) agents often ground their responses on external knowledge bases (KBs). These KBs can be dynamic and may be updated frequently. Existing approaches for le…

cs.CL2024

SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models

Vipul Rathore, Aniruddha Deb, Ankish Chandresh +2

Recently, very large language models (LLMs) have shown exceptional performance on several English NLP tasks with just in-context learning (ICL), but their utility in other language…

cs.LG2020

Symbolic Network: Generalized Neural Policies for Relational MDPs

Sankalp Garg, Aniket Bajpai, Mausam

A Relational Markov Decision Process (RMDP) is a first-order representation to express all instances of a single probabilistic planning domain with possibly unbounded number of obj…

cs.AI2018

Block-Value Symmetries in Probabilistic Graphical Models

Gagan Madan, Ankit Anand, Mausam +1

One popular way for lifted inference in probabilistic graphical models is to first merge symmetric states into a single cluster (orbit) and then use these for downstream inference,…

cs.CL2020

IMoJIE: Iterative Memory-Based Joint Open Information Extraction

Keshav Kolluru, Samarth Aggarwal, Vipul Rathore +2

While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task. Our work builds upon CopyAttent…

cs.AI2023

NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs

Ishaan Singh, Navdeep Kaur, Garima Gaur +1

While Knowledge Graph Completion (KGC) on static facts is a matured field, Temporal Knowledge Graph Completion (TKGC), that incorporates validity time into static facts is still in…

cs.CL2024

DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles

Tanishq Gupta, Mohd Zaki, Devanshi Khatsuriya +3

A crucial component in the curation of KB for a scientific domain (e.g., materials science, foods & nutrition, fuels) is information extraction from tables in the domain's publishe…

cs.CL2021

MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction

Tanishq Gupta, Mohd Zaki, N. M. Anoop Krishnan +1

An overwhelmingly large amount of knowledge in the materials domain is generated and stored as text published in peer-reviewed scientific literature. Recent developments in natural…

cs.AI2022

Matching Papers and Reviewers at Large Conferences

Kevin Leyton-Brown, Mausam, Yatin Nandwani +4

Peer-reviewed conferences, the main publication venues in CS, rely critically on matching highly qualified reviewers for each paper. Because of the growing scale of these conferenc…

cs.LG2021

Unsupervised Learning of KB Queries in Task-Oriented Dialogs

Dinesh Raghu, Nikhil Gupta, Mausam

Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses. Exis…

cs.CL2021

Regex Queries over Incomplete Knowledge Bases

Vaibhav Adlakha, Parth Shah, Srikanta Bedathur +1

We propose the novel task of answering regular expression queries (containing disjunction () and Kleene plus () operators) over incomplete KBs. The answer set of these que…

cs.CL2020

Large Scale Question Answering using Tourism Data

Danish Contractor, Krunal Shah, Aditi Partap +2

We introduce the novel task of answering entity-seeking recommendation questions using a collection of reviews that describe candidate answer entities. We harvest a QA dataset that…

cs.LG2019

Size Independent Neural Transfer for RDDL Planning

Sankalp Garg, Aniket Bajpai, Mausam

Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from…

cs.AI2014

Topological Value Iteration Algorithms

Peng Dai, Mausam, Daniel Sabby Weld +1

Value iteration is a powerful yet inefficient algorithm for Markov decision processes (MDPs) because it puts the majority of its effort into backing up the entire state space, whic…

cs.LG2023

A Solver-Free Framework for Scalable Learning in Neural ILP Architectures

Yatin Nandwani, Rishabh Ranjan, Mausam +1

There is a recent focus on designing architectures that have an Integer Linear Programming (ILP) layer within a neural model (referred to as Neural ILP in this paper). Neural ILP a…

cs.AI2021

Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment

Harkanwar Singh, Prachi Jain, Mausam +1

Knowledge Graph Completion (KGC) predicts missing facts in an incomplete Knowledge Graph. Almost all of existing KGC research is applicable to only one KG at a time, and in one lan…

cs.RO2021

ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis

Rajas Bansal, Shreshth Tuli, Rohan Paul +1

A robot working in a physical environment (like home or factory) needs to learn to use various available tools for accomplishing different tasks, for instance, a mop for cleaning a…

cs.CL2025

Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction

Vipul Rathore, Malik Hammad Faisal, Parag Singla +1

Distantly Supervised Relation Extraction (DSRE) remains a long-standing challenge in NLP, where models must learn from noisy bag-level annotations while making sentence-level predi…

cs.RO2021

TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators

Shreshth Tuli, Rajas Bansal, Rohan Paul +1

Robots assisting us in factories or homes must learn to make use of objects as tools to perform tasks, e.g., a tray for carrying objects. We consider the problem of learning common…

cs.AI2016

A Programming Language With a POMDP Inside

Christopher H. Lin, Mausam, Daniel S. Weld

We present POAPS, a novel planning system for defining Partially Observable Markov Decision Processes (POMDPs) that abstracts away from POMDP details for the benefit of non-expert…

cs.CL2024

Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning

Mayur Patidar, Riya Sawhney, Avinash Singh +3

Existing Knowledge Base Question Answering (KBQA) architectures are hungry for annotated data, which make them costly and time-consuming to deploy. We introduce the problem of few-…

cs.AI2012

A Theory of Goal-Oriented MDPs with Dead Ends

Andrey Kolobov, Mausam, Daniel Weld

Stochastic Shortest Path (SSP) MDPs is a problem class widely studied in AI, especially in probabilistic planning. They describe a wide range of scenarios but make the restrictive…

cs.CL2023

Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions

Mayur Patidar, Prayushi Faldu, Avinash Singh +3

When answering natural language questions over knowledge bases, missing facts, incomplete schema and limited scope naturally lead to many questions being unanswerable. While answer…

cs.CL2020

A Simple Yet Strong Pipeline for HotpotQA

Dirk Groeneveld, Tushar Khot, Mausam +1

State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named enti…

cs.AI2026

Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery

Harshit Bisht, Vinay Kumar, Kevin Maik Jablonka +2

A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they already function as co-scientists,…

cs.CL2024

MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations

Vishal Vivek Saley, Goonjan Saha, Rocktim Jyoti Das +2

Medical task-oriented dialogue systems can assist doctors by collecting patient medical history, aiding in diagnosis, or guiding treatment selection, thereby reducing doctor burnou…

cs.CL2022

"Covid vaccine is against Covid but Oxford vaccine is made at Oxford!" Semantic Interpretation of Proper Noun Compounds

Keshav Kolluru, Gabriel Stanovsky, Mausam

Proper noun compounds, e.g., "Covid vaccine", convey information in a succinct manner (a "Covid vaccine" is a "vaccine that immunizes against the Covid disease"). These are commonl…

cs.AI2014

A Heuristic Search Approach to Planning with Continuous Resources in Stochastic Domains

Nicolas Meuleau, Emmanuel Benazera, Ronen I. Brafman +2

We consider the problem of optimal planning in stochastic domains with resource constraints, where the resources are continuous and the choice of action at each step depends on res…

cs.AI2024

Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion

Ananjan Nandi, Navdeep Kaur, Parag Singla +1

High-quality and high-coverage rule sets are imperative to the success of Neuro-Symbolic Knowledge Graph Completion (NS-KGC) models, because they form the basis of all symbolic inf…

cs.RO2022

ToolTango: Common sense Generalization in Predicting Sequential Tool Interactions for Robot Plan Synthesis

Shreshth Tuli, Rajas Bansal, Rohan Paul +1

Robots assisting us in environments such as factories or homes must learn to make use of objects as tools to perform tasks, for instance using a tray to carry objects. We consider…

cs.AI2017

Octopus: A Framework for Cost-Quality-Time Optimization in Crowdsourcing

Karan Goel, Shreya Rajpal, Mausam

We present Octopus, an AI agent to jointly balance three conflicting task objectives on a micro-crowdsourcing marketplace - the quality of work, total cost incurred, and time to co…

cs.CL2020

Why and when should you pool? Analyzing Pooling in Recurrent Architectures

Pratyush Maini, Keshav Kolluru, Danish Pruthi +1

Pooling-based recurrent neural architectures consistently outperform their counterparts without pooling. However, the reasons for their enhanced performance are largely unexamined.…

cs.AI2026

MDGYM: Benchmarking AI Agents on Molecular Simulations

Vinay Kumar, Satyendra Rajput, Mausam +1

The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin modern science. Molecular dy…

cs.CV2024

MeasureNet: Measurement Based Celiac Disease Identification

Aayush Kumar Tyagi, Vaibhav Mishra, Ashok Tiwari +5

Celiac disease is an autoimmune disorder triggered by the consumption of gluten. It causes damage to the villi, the finger-like projections in the small intestine that are responsi…

cs.AI2025

FCoReBench: Can Large Language Models Solve Challenging First-Order Combinatorial Reasoning Problems?

Chinmay Mittal, Krishna Kartik, Mausam +1

Can the large language models (LLMs) solve challenging first-order combinatorial reasoning problems such as graph coloring, knapsack, and cryptarithmetic? By first-order, we mean t…

cs.CL2022

PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction

Vipul Rathore, Kartikeya Badola, Mausam +1

Neural models for distantly supervised relation extraction (DS-RE) encode each sentence in an entity-pair bag separately. These are then aggregated for bag-level relation predictio…

cs.CL2022

CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion

Keshav Kolluru, Mayank Singh Chauhan, Yatin Nandwani +2

Pre-trained language models (LMs) like BERT have shown to store factual knowledge about the world. This knowledge can be used to augment the information present in Knowledge Bases,…

cs.CL2025

Iterative Repair with Weak Verifiers for Few-shot Transfer in KBQA with Unanswerability

Riya Sawhney, Samrat Yadav, Indrajit Bhattacharya +1

Real-world applications of KBQA require models to handle unanswerable questions with a limited volume of in-domain labeled training data. We propose the novel task of few-shot tran…

cs.AI2021

End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks

Ananye Agarwal, Pradeep Shenoy, Mausam

Neural models and symbolic algorithms have recently been combined for tasks requiring both perception and reasoning. Neural models ground perceptual input into a conceptual vocabul…