Papers by Mohna Chakraborty

3 papers
Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked? (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on Large Language Models (LLMs) have not investigated the impact of question types on LLM performance.
Approach: They evaluate the performance of five Large Language Models on reasoning tasks . they use quantitative reasoning tasks and deductive reasoning tasks to evaluate the models .
Outcome: The results show that Reasoning accuracy does not correlate with final selection accuracy.
Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly deployed in domains requiring moral understanding, yet their reasoning often remains shallow and misaligned with human reasoning.
Approach: They propose a value-grounded framework for evaluating and distilling structured moral reasoning in large language models.
Outcome: The proposed framework evaluates 12 open-source models across four moral datasets.
Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task.
Approach: They propose to use few-shot learning settings to fine-tune the sentiment classification model using manual or automatically generated prompts.
Outcome: The proposed method outperforms the base prompt and the prompts generated using few-shot learning for the binary sentence-level sentiment classification task.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations