Papers by Subhabrata Dutta
Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) and AI assistants are experiencing exponential growth in usage among expert and amateur users. |
| Approach: | They propose to assess the reliability of current Large Language Models as science communicators . they use a dataset comprising 742 Yes/No queries embedded in complex scientific concepts . |
| Outcome: | The proposed model outperforms open-access models in scientific question-answering tasks . the model outpersforms GPT-4 Turbo models in many evaluation aspects . |
Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have transformed NLP with their remarkable In-context Learning capabilities. |
| Approach: | They propose to use large language models to generalize from labeled examples of predefined tasks to novel tasks . they use biological neurons and the Transformer architecture to study the potential for information sharing across tasks. |
| Outcome: | The proposed model can generalize from labeled examples of predefined tasks to novel tasks despite no examples from the target task in the context. |
Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment (2023.acl-long)
Copied to clipboard
| Challenge: | a handful of studies have explored ICL in a cross-lingual setting . emergence of large-scale, pretrained, Transformer-based language models has marked the commencement of an avant-garde era in NLP. |
| Approach: | They propose a novel prompt construction strategy to bridge the gap between ICL and cross-lingual text classification. |
| Outcome: | The proposed approach outperforms random prompt selection by a large margin across three tasks using 44 different cross-lingual pairs. |
LM2: A Simple Society of Language Models Solves Complex Reasoning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that providing guidance via decomposing the original question into multiple subproblems elicits more robustness in LLM reasoning. |
| Approach: | They propose a language-based decomposition, solution and verification framework that modularizes the decomposer, solution, and verification into three different language models. |
| Outcome: | The proposed model outperforms existing methods on in- and out-domain reasoning problems, outperforming the best baselines by 8.1% on MATH, 7.71% on JEEBench, and 9.7% on MedQA problems. |
Patches of Nonlinearity: Instruction Vectors in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Despite the success of instruction-tuned language models, little is known about how they process instructions internally. |
| Approach: | They propose a method to localize instruction processing in language models that is free from patching assumptions. |
| Outcome: | The proposed method disentangles the implicit linear assumptions of patching-based techniques. |
Reward Modeling for Scientific Writing Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models for scientific writing evaluation are primarily optimized for general-purpose benchmarks with fixed scoring rubrics and evaluation criteria. |
| Approach: | They propose to train scientific writing evaluation models that leverage domain knowledge . they use a two-stage evaluation framework that optimizes evaluation preferences and refines reasoning capabilities . |
| Outcome: | The proposed model generalizes effectively across tasks and to previously unseen settings. |
Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining? (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for argument mining are limited by the scarcity of manually annotated data and the highly domain-dependent nature of argumentation. |
| Approach: | They propose a novel transfer learning strategy to fine tune pretrained Transformer-based Language Models on a selectively masked language modeling task and a new prompt-based strategy for inter-component relation prediction. |
| Outcome: | The proposed method outperforms existing models on both within- and out-of-domain datasets while leveraging on the discourse context. |
Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent attempts at prompt decomposition toward solving complex, multi-step reasoning problems depend on the ability of the LLM to simultaneously decompose and solve the problem. |
| Approach: | They propose a decomposition generator that decomposes complex problems into subproblems that require fewer reasoning steps. |
| Outcome: | The proposed method can produce competitive or even better performance compared to its larger successor, GPT-4. |
Data-scarce Behavior Editing of Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior studies show that noisy neural circuitries coexist with generalizable abilities within LLMs. |
| Approach: | a new method is proposed to improve the generalizability of large-scale web-based text models . a TaRot method is based on learnable rotation matrices optimized for Bayesian optimization . |
| Outcome: | a new method for task adaptation improves on multiple classification and generation tasks . it improves upon zero- and few-shot performance, with average improvements of 14% and 15% . |