Papers by Soham Dan
CRAFT: Training-Free Cascaded Retrieval for Tabular QA (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for open-domain table question answering require retraining or fine-tuning on new datasets. |
| Approach: | They propose a zero-shot, cascaded retrieval approach that uses a sparse retrieval model to filter a subset of candidates before applying more expensive dense models as re-rankers. |
| Outcome: | The proposed method outperforms state-of-the-art retrieval models on the NQ-Tables dataset. |
Compositional Data and Task Augmentation for Instruction Following (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that understand spatial concepts and compositional language are inadequate for executing natural language instructions in a physically grounded domain. |
| Approach: | They propose to use knowledge-free auxiliary signals to help the model understand compositional instructions and provide supervision for the instruction's components. |
| Outcome: | The proposed model correctly identifies the source block while the existing model fails on this example. |
Are Large Language Models Effective in Clinical Trial Design? A Study on Baseline Feature Generation (2025.findings-naacl)
Copied to clipboard
Nafis Neehal, Bowen Wang, Shayom Debopadhaya, Corey Curran, Keerthiram Murugesan, Soham Dan, Vibha Anand, Kristin Bennett
| Challenge: | Clinical trials require baseline features to characterize participants and ensure accurate study outcomes. |
| Approach: | They evaluate LLMs' ability to generate appropriate baseline features for clinical trials . they use CT-Repo and CT-Pub datasets to generate features from clinical trials. |
| Outcome: | The proposed framework improves the performance of the baseline feature generation model on a clinical trial. |
A Survey of Toxicity Mitigation Strategies for Multilingual Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models can reproduce and amplify toxic content, including hate speech, harassment, and bias. |
| Approach: | They propose a comprehensive survey of the many detoxification methods tailored to multilingual LLMs. |
| Outcome: | The proposed methods are based on data filtering, style transfer, expert-based logit steering, retrieval augmentation, and human feedback. |
NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models (2024.findings-acl)
Copied to clipboard
Amit Dhurandhar, Tejaswini Pedapati, Ronny Luss, Soham Dan, Aurelie Lozano, Payel Das, Georgios Kollias
| Challenge: | Transformer-based Language Models have become ubiquitous in natural language processing due to impressive performance on various tasks. |
| Approach: | They explore how sparsity affects network topology by exploiting mechanisms seen in biological networks . they show that model-agnostic sparsities are performant across diverse NLP tasks . |
| Outcome: | The proposed model-agnostic sparsity approaches are performant and efficient across NLP tasks. |
Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval over haystacks (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing multilingual long-context benchmarks are myopic and inherently limited, as successful recall alone does not indicate a model’s capacity to reason over extended contexts. |
| Approach: | They propose a new synthetic benchmark for multilingual long-context reasoning that includes bAbI-style tasks that test multi-hop inference, aggregation, and epistemic reasoning. |
| Outcome: | The proposed benchmarks are based on a multilingual long-context model and span seven languages. |
Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent large language models demonstrate remarkable abilities in responding to queries in diverse languages, but their ability to handle long multilingual contexts is unexplored. |
| Approach: | They propose a multilingual Needle-in-a-Haystack (MLNeedle) test to assess a model's ability to retrieve relevant information from a collection of multilingual distractor texts. |
| Outcome: | The proposed model performance is the lowest when the needle is in a language outside the English language family and (ii) located in the middle of the input context. |
From Spatial Relations to Spatial Configurations (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing spatial representations are not sufficient for describing complex spatial configurations. |
| Approach: | They propose to integrate existing spatial representation languages with an annotation schema to extend the capabilities of existing ones. |
| Outcome: | The proposed language can represent a large set of spatial concepts crucial for reasoning . it integrates with the Abstract Meaning Representation (AMR) annotation schema and annotates text from diverse datasets . |
MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. |
| Approach: | They propose a multilingual guardrail with reasoning for prompt classification that integrates culturally and linguistically nuanced variants and supervised fine-tuning. |
| Outcome: | The proposed guardrail outperforms baselines across in-domain and out-of-domain languages by more than 15%. |
MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types (2023.findings-acl)
Copied to clipboard
Keerthiram Murugesan, Sarathkrishna Swaminathan, Soham Dan, Subhajit Chaudhury, Chulaka Gunasekara, Maxwell Crouse, Diwakar Mahajan, Ibrahim Abdelaziz, Achille Fokoue, Pavan Kapanipathi, Salim Roukos, Alexander Gray
| Challenge: | Existing evaluation metrics for machine text are inadequate to capture quality of text . a recent study has focused on task-specific evaluation metrics or on properties of machine-generated text based on mismatch errors . |
| Approach: | They propose a new evaluation scheme based on fine-grained mismatch errors . they propose 13 mismatch error types to guide the model for better prediction of human judgments . |
| Outcome: | The proposed evaluation scheme is based on mismatch errors in 7 NLP tasks . the mismatch error types guide the model for better prediction of human judgments . |
Understanding Spatial Relations through Multiple Modalities (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on common sense reasoning and understanding of spatial relations is limited. |
| Approach: | They propose a spatial model that uses both textual and visual information to predict spatial relations between two entities in an image. |
| Outcome: | The proposed model improves prediction accuracy and coverage and deals with unseen subjects, objects and relations. |
On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning (2025.coling-main)
Copied to clipboard
| Challenge: | Text-based reinforcement learning is a form of interactive fiction where players manipulate the environment using text and admissible actions in natural language. |
| Approach: | They show that rich semantic understanding leads to efficient training of text-based RL agents . they also show that semantic degeneration occurs when LMs are inappropriately fine-tuned . |
| Outcome: | The results suggest that semantic understanding is not important for the task . they also show that fine-tuning language models can degenerate the agent's performance . |
On the Effects of Transformer Size on In- and Out-of-Domain Calibration (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Large pre-trained transformer language models are notoriously expensive to train . prior work has developed smaller, more compact models to reduce training costs . |
| Approach: | They propose to develop smaller, more compact transformer language models which can be calibrated in-domain . they show that smaller models can achieve competitive calibration compared to larger models . |
| Outcome: | The proposed models achieve competitive calibration and better calibration than larger models on a wide range of tasks. |
Generalization in Instruction Following Systems (2021.naacl-main)
Copied to clipboard
| Challenge: | Understanding and executing natural language instructions in a grounded domain is one of the hallmarks of artificial intelligence. |
| Approach: | They propose a learning strategy that involves data augmentation to improve the model's performance. |
| Outcome: | The proposed learning strategy outperforms state-of-the-art models in the blocks world domain while satisfying our expectations much better. |
A Locally Linear Procedure for Word Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to learn word embeddings of two languages are limited by the expressiveness of the translation model. |
| Approach: | They propose an algorithm that uses multiple orthogonal translation matrices to model the mapping and derive an algorithm to learn these multiple matric. |
| Outcome: | The proposed algorithm achieves better performance in bilingual and cross-lingual word translation tasks compared to the single matrix baseline. |
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing (2023.acl-short)
Copied to clipboard
| Challenge: | Existing studies show that state-of-the-art NLP models are vulnerable to adversarial attacks . label smoothing has been proven effective in a variety of applications and modalities . |
| Approach: | They propose to use label smoothing to improve adversarial robustness in pre-trained models against various popular attacks. |
| Outcome: | The proposed method significantly improves adversarial robustness in pre-trained models against various popular attacks. |
Few-Shot Novel Concept Learning for Semantic Parsing (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing deep learning algorithms typically require thousands of examples to learn novel concepts. |
| Approach: | They propose an algorithm for learning novel concepts by representing them as programs over existing concepts. |
| Outcome: | The proposed approach outperforms end-to-end neural semantic parsers in a few-shot novel concept learning setting. |
AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion Generation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Assertions have been the de facto collateral for hardware for over a decade. |
| Approach: | They propose a benchmark to evaluate LLMs’ effectiveness for assertion generation quantitatively. |
| Outcome: | The proposed benchmark compares state-of-the-art LLMs with existing benchmarks and shows that they generate higher fractions of functionally correct assertions. |
API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs (2024.acl-long)
Copied to clipboard
Kinjal Basu, Ibrahim Abdelaziz, Subhajit Chaudhury, Soham Dan, Maxwell Crouse, Asim Munawar, Vernon Austel, Sadhana Kumaravel, Vinod Muthusamy, Pavan Kapanipathi, Luis Lastras
| Challenge: | Existing methods to train and test large language models that involve calls to tools and APIs are lacking. |
| Approach: | They propose a large corpora for training and systematic testing of tool-augmented LLMs. |
| Outcome: | The proposed datasets mimic real-world scenarios involving API-tasks and slot filling. |
Language Guided Exploration for RL Agents in Text Environments (2024.findings-naacl)
Copied to clipboard
| Challenge: | Real-world sequential decision making is characterized by sparse rewards and large decision spaces. |
| Approach: | They introduce a language-based framework that provides decision-level guidance to an RL agent. |
| Outcome: | The proposed framework outperforms vanilla RL agents on ScienceWorld in 2022. |