Papers by Harsh Gupta
TRANSIENTTABLES: Evaluating LLMs’ Reasoning on Temporally Evolving Semi-structured Tables (2025.naacl-long)
Copied to clipboard
| Challenge: | a recent study shows that large language models are limited in their ability to reason over time due to static datasets. |
| Approach: | They present a dataset that includes 3,971 questions derived from over 14,000 tables . they introduce a template-based question-generation pipeline that harnesses LLMs to refine questions . |
| Outcome: | The proposed model improves on the TRANSIENTTABLES dataset . it demonstrates that the model can reason over time, even when it is not static . |
Multimodal Persona Based Generation of Comic Dialogs (2023.acl-long)
Copied to clipboard
| Challenge: | Existing models for persona based dialogue generation for comic strips encode two-party dialogues and do not account for visual information. |
| Approach: | They propose a multimodal persona-based architecture to generate dialogues for the next panel in comic strips. |
| Outcome: | The proposed paradigm reduces the perplexity score by 10 points over existing models . the novel dataset, ComSet, contains 54K comic strips . |
Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for target-guided response generation are inconsistent with human judgement ratings. |
| Approach: | They propose a technique that finds a bridging path between the source and target and uses it to generate transition responses. |
| Outcome: | The proposed technique outperforms baselines on target-guided response generation task. |
Unsupervised Multi-View Post-OCR Error Correction With Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Prior work used text generation techniques or redundancy in similar passages for OCR error correction, which is not appropriate in cases of low corpus redundancies or weak document contextual information. |
| Approach: | They propose to use a pretrained language model to reconcile different OCR views in unsupervised way so that their combination contains fewer errors than each individual view. |
| Outcome: | The proposed model can reconcile multiple OCR views so that their combined version contains fewer errors than the best OCR view. |