Papers by Abhijit Mishra
Eyes Show the Way: Modelling Gaze Behaviour for Hallucination Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection depend on knowledge sources that are explicit such as Wikipedia or knowledge graphs. |
| Approach: | They propose a cognitive approach that leverages gaze signals from humans to detect hallucinations in natural language processing (NLP) they collect and introduce an eye tracking corpus consisting of 500 instances, annotated by five annotators for hallucinism detection. |
| Outcome: | The proposed approach achieves a balanced accuracy of 87.1% on a FactCC dataset. |
Understand the Implication: Learning to Think for Pragmatic Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods rely on annotated labels but overlook the reasoning process humans naturally use to interpret implicit meaning. |
| Approach: | They propose a dataset that includes explicit reasoning for both correct and incorrect interpretations and propose supervised fine-tuning to improve their performance. |
| Outcome: | The proposed dataset improves LLMs' pragmatic understanding by 11.12% across model families and 16.10% over label trained models. |
Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs) (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in NLP driven by powerful Large Language Models such as Ope-nAI GPT-4 have been demonstrated in ALS and stroke patients. |
| Approach: | They propose to use instruction-tuned Large Language Models (LLMs) with EEG data to decode and express brain activity in a comprehensible form. |
| Outcome: | The proposed approach enables multimodal description generation from EEG data and further refinement on embeddings to generate text directly from EMG during inference. |
Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour (P18-1)
Copied to clipboard
Sandeep Mathias, Diptesh Kanojia, Kevin Patel, Samarth Agrawal, Abhijit Mishra, Pushpak Bhattacharyya
| Challenge: | Existing methods to predict text quality include estimating subjective aspects of text, like structure, clarity, etc. |
| Approach: | They propose to capture gaze behaviour to help predict text quality by reporting improvements obtained by adding gaze features to traditional textual features for score prediction. |
| Outcome: | The proposed model shows that capturing gaze behaviour improves the accuracy of score prediction when the reader has fully understood the text. |
Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective (P19-4)
Copied to clipboard
| Challenge: | tutorial aims to explain the basic concepts of translating structured data into natural language . Various solutions for structured data translation will be discussed . |
| Approach: | tutorial aims to cover foundational, methodological, and system development aspects of translating structured data into natural language . Various solutions starting from traditional rule based/heuristic driven and modern data-driven will be discussed . |
| Outcome: | The tutorial aims to convey challenges and nuances in structured data translation, data representation techniques, and domain adaptable solutions for translation of the data into natural language form. |
Happy Are Those Who Grade without Seeing: A Multi-Task Learning Approach to Grade Essays Using Gaze Behaviour (2020.aacl-main)
Copied to clipboard
| Challenge: | Using gaze behaviour to solve automatic essay grading tasks is costly in terms of time and money. |
| Approach: | They propose to collect gaze behaviour from 48 essays and learn gaze behaviour for the rest of the essays using a multi-task learning framework. |
| Outcome: | The proposed approach achieves a statistically significant improvement over the state-of-the-art system for the essay sets where gaze data is available. |
A Modular Architecture for Unsupervised Sarcasm Generation (D19-1)
Copied to clipboard
| Challenge: | Existing systems for sarcasm generation are elusive due to the fact that both selection of contents and training of sarcasm are based on the same data. |
| Approach: | They propose a framework that takes a literal negative opinion as input and translates it into a sarcastic version. |
| Outcome: | The proposed system outperforms baselines built using known unsupervised statistical and neural machine translation and style transfer techniques. |
ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries (2025.acl-long)
Copied to clipboard
Kishan Maharaj, Vitobha Munigala, Srikanth G. Tamilselvam, Prince Kumar, Sayandeep Sen, Palani Kodeswaran, Abhijit Mishra, Pushpak Bhattacharyya
| Challenge: | Recent advances in large language models have significantly enhanced their ability to understand both natural language and code, but are prone to hallucinations. |
| Approach: | They propose a first-of-its-kind dataset, CodeSumEval, with 10K samples, curated specifically for hallucination detection in code summarisation. |
| Outcome: | The proposed framework has a 73% F1 score and is curated specifically for detection of hallucinations in code summarisation. |
Unsupervised Neural Text Simplification (P19-1)
Copied to clipboard
| Challenge: | Existing unsupervised methods for text simplification are limited to unlabeled text . paper aims to improve the performance of unsupervised systems by incorporating labeled pairs . |
| Approach: | They propose to use unlabeled text to train a neural text simplification framework . they propose to add a pair of attentional-decoders to the framework to improve performance . |
| Outcome: | The proposed model outperforms existing supervised methods on public test data. |
Addressing Bias and Hallucination in Large Language Models (2024.lrec-tutorials)
Copied to clipboard
Nihar Ranjan Sahoo, Ashita Saxena, Kishan Maharaj, Arif A. Ahmad, Abhijit Mishra, Pushpak Bhattacharyya
| Challenge: | This tutorial provides a comprehensive overview of two critical aspects of Large Language Models: bias and hallucination. |
| Approach: | This tutorial provides an overview of two critical aspects of Large Language Models: bias and hallucination. |
| Outcome: | This tutorial delves into the complex dimensions of Large Language Models (LLMs) it outlines ethical considerations pertinent to their development and discusses hallucination, a prevalent issue in generative AI systems such as LLMs. |