Papers by Somak Aditya

NLKI: A Lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks (2025.findings-emnlp)

Copied to clipboard

Aritra Dutta, Swapnanil Mukherjee, Deepanway Ghosal, Somak Aditya

Responsible & Trustworthy NLP

Challenge:	Small vision-language models lag behind their larger generative counterparts due to lack of knowledge.
Approach:	They propose a framework that integrates commonsense knowledge into small vision-language models . the framework retrieves natural language facts and prompts an LLM to craft natural language explanations .
Outcome:	The proposed framework retrieves natural language facts and prompts an LLM to craft natural language explanations.

EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos (2025.emnlp-main)

Copied to clipboard

Sourjyadip Ray, Shubham Sharma, Somak Aditya, Pawan Goyal

Multimodality

Challenge:	This paper explores using Multimodal Large Language Models (MLLMs) to respond to student questions from online lectures . MLLM is a novel question answering task of real world significance .
Approach:	They propose to use Multimodal Large Language Models to automatically respond to student questions from online lectures by using a dataset of 5252 question-answer pairs from 296 computer science videos.
Outcome:	The proposed model can fine tune and fine tune questions from 296 computer science videos and show that students' preferences are important to the task.

Vector Space Interpolation for Query Expansion (2022.aacl-short)

Copied to clipboard

Deepanway Ghosal, Somak Aditya, Sandipan Dandapat, Monojit Choudhury

Representation Learning

Challenge:	Topic-sensitive query set expansion is crucial for queries related to sensitive and emerging topics.
Approach:	They propose a method for topic-sensitive query set expansion using vector space interpolation.
Outcome:	The proposed method generates new queries about the sensitive topic by incorporating set diversity, which is not captured by traditional sentence-level augmentation methods such as paraphrasing or back-translation.

Multilingual CheckList: Generation and Evaluation (2022.findings-aacl)

Copied to clipboard

Karthikeyan K, Shaily Bhatt, Pankaj Singh, Somak Aditya, Sandipan Dandapat, Sunayana Sitaram, Monojit Choudhury

Multilinguality

Challenge:	Multilingual evaluation benchmarks usually contain limited high-resource languages and do not test models for specific linguistic capabilities.
Approach:	They propose an algorithm for automatically extracting target language CheckList templates from machine translated instances of a source language templates.
Outcome:	The proposed algorithm compares with CheckLists created with human verification in Hindi and 9 other languages.

Evaluating LLMs’ Mathematical and Coding Competency through Ontology-guided Interventions (2025.findings-acl)

Copied to clipboard

Pengfei Hong, Navonil Majumder, Deepanway Ghosal, Somak Aditya, Rada Mihalcea, Soujanya Poria

Semantic Text Processing

Challenge:	Current large language models have shown impressive performance on logical reasoning benchmarks . however, the true depth of their competencies and robustness in reasoning tasks remains an open question .
Approach:	They propose a general ontology of perturbations and a semi-automatic method to apply perturbations to arithmetic reasoning and code generation datasets to test their LLMs' capabilities.
Outcome:	The proposed model outperforms existing models on arithmetic reasoning and code generation tasks.

A Robust Information-Masking Approach for Domain Counterfactual Generation (2023.findings-acl)

Copied to clipboard

Pengfei Hong, Rishabh Bhardwaj, Navonil Majumder, Somak Aditya, Soujanya Poria

Semantic Text Processing

Challenge:	Domain shift is a big challenge in NLP, but many approaches fail to leverage domain-specific nuances relevant to the task at hand.
Approach:	They propose a method that uses frequency-based masking to transform a text from the source domain to a target domain.
Outcome:	The proposed method outperforms baselines on 10 out of 12 domain-counterfactual classification settings with an average of 1.7% improvement in accuracy metric.

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs (2024.emnlp-main)

Copied to clipboard

Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych

Semantic Text Processing

Challenge:	Recent prompting techniques have improved LLMs’ performance on various reasoning tasks, but there is little understanding of what triggers reasoning abilities in LLM in the inference stage.
Approach:	They propose a method that transforms a natural language problem into code and directly prompts the LLM using the generated code without resorting to external code execution.
Outcome:	The proposed method boosts multiple LLMs by 22.52 percentage points on GPT 3.5, 7.75 on Mixtral, and 16.78 on Mistral.

ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital Environments (2024.emnlp-main)

Copied to clipboard

Sourjyadip Ray, Kushal Gupta, Soumi Kundu, Dr Kasat, Somak Aditya, Pawan Goyal

Multimodality

Challenge:	a global shortage of healthcare workers has demanded the development of smart healthcare assistants.
Approach:	They analyze the healthcare knowledge of existing Large Vision Language Models (LVLMs) using an annotated open-ended task.
Outcome:	The study analyzes the knowledge of large vision language models using open-ended questions . the results highlight the need for specialized, domain-specific solutions .

MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning (2024.naacl-long)

Copied to clipboard

Debrup Das, Debopriyo Banerjee, Somak Aditya, Ashish Kulkarni

Reasoning

Challenge:	TALMs have been successfully employed in question-answering benchmarks, but their efficacy on complex mathematical reasoning benchmarks are open research questions.
Approach:	They propose a tool-augmented large language model for mathematical reasoning that enhances the skillset of large language models (LLMs) by 13.5%.
Outcome:	The proposed model achieves better accuracy and better knowledge retrieval performance than existing tools.

SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation (2025.naacl-long)

Copied to clipboard

Saurabh Kumar Pandey, Sachin Vashistha, Debrup Das, Somak Aditya, Monojit Choudhury

Robustness in NLP

Challenge:	a scalable approach to classify text with sensitivity is costly because of exponential time complexity.
Approach:	They propose a framework for calculating word-level local and global sensitivities . they use a CHECKLIST-generated sentiment analysis dataset to test their approach .
Outcome:	The proposed framework can be used to calculate word-level local and global sensitivities . it improves attacks by 15.58%, while using sensitivity as an additional reward improves .

Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks (2024.lrec-main)

Copied to clipboard

Abhinav Sukumar Rao, Atharva Roshan Naik, Sachin Vashistha, Somak Aditya, Monojit Choudhury

Responsible & Trustworthy NLP

Challenge:	Existing methods to jailbreak large language models have been poorly studied . a recent study showed that non-expert users can jailbreak LLMs by manipulating their prompts .
Approach:	They propose a formalism and a taxonomy of known (and possible) jailbreaks . they propose generating a dataset of model outputs across 3700 jailbreak prompts a 'prompt' attack is a new attack popularly categorized as "prompting injection attacks"
Outcome:	The proposed model exploits 3700 jailbreak prompts over 4 tasks to analyze their effectiveness . authors show that the model can learn to perform a new task on unseen examples .