Papers by Rishabh Gupta
Deep Learning Based Named Entity Recognition Models for Recipes (2024.lrec-main)
Copied to clipboard
Ayush Agarwal, Janak Kapuriya, Shubham Agrawal, Akhil Vamshi Konam, Mansi Goel, Rishabh Gupta, Shrey Rastogi, Niharika Niharika, Ganesh Bagler
| Challenge: | Named entity recognition is a technique for extracting information from unstructured data with known labels. |
| Approach: | They use named entity recognition to annotate ingredients from recipe data . they use a clustering-based approach to annnotate 88,526 phrases . |
| Outcome: | The proposed method improves on a dataset of 88,526 phrases from RecipeDB . the fine-tuned spaCy-transformer performs better than the previous methods . |
Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk Appetite? (2025.emnlp-industry)
Copied to clipboard
Divij Chawla, Ashita Bhutada, Duc Anh Do, Abhinav Raghunathan, Vinod Sp, Cathy Guo, Dar Win Liew, Prannaya Gupta, Rishabh Bhardwaj, Rajat Bhardwaj, Soujanya Poria
| Challenge: | Our analysis was conducted on proprietary systems and open-weight models . FINRISKEVAL analyzed 1,720 profiles spanning a broad spectrum of possible risk categories . |
| Approach: | They evaluated proprietary AI systems and open-weight models to assess investment risk appetite using carefully curated user profiles. |
| Outcome: | The proposed models exhibit significant variance when user attributes that should not influence risk computation are changed. |
Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation (2023.acl-long)
Copied to clipboard
| Challenge: | a counterspeech with a certain intent may not be sufficient in every situation due to complex nature of hate speech . a novel framework for intent-conditioned counterseech generation is proposed to address the pervasive issue of hateful speech on the internet. |
| Approach: | They propose a framework for intent-conditioned counterspeech generation that leverages intent-specific representations and a fusion module to incorporate intent-related information into the model. |
| Outcome: | The proposed framework outperforms baselines by 10% across evaluation metrics. |
WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models (2024.emnlp-demo)
Copied to clipboard
Prannaya Gupta, Le Yau, Hao Low, I-Shiang Lee, Hugo Lim, Yu Teoh, Koh Hng, Dar Liew, Rishabh Bhardwaj, Rajat Bhardwaj, Soujanya Poria
| Challenge: | Potential harms include training data leakage, biases in responses and decision-making, and unauthorized use for purposes such as terrorism and the generation of sexually explicit content. |
| Approach: | WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models. |
| Outcome: | The framework supports both LLM and judge benchmarking and incorporates custom mutators to test safety against various text-style mutations such as future tense and paraphrasing. |
Adding SPICE to Life: Speaker Profiling in Multiparty Conversations (2024.lrec-main)
Copied to clipboard
| Challenge: | Prior studies assumed the speaker’s persona’s immediate availability, a premise not universally applicable. |
| Approach: | They propose to synthesize persona attributes for each dialogue participant by combining three core tasks: persona discovery, persona-type identification, and persona value extraction. |
| Outcome: | The proposed task synthesizes persona attributes for each dialogue participant . the resulting model is compared against a baseline model and the proposed model is robust. |
Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language model (LLM) approaches to tabular summarization rely on prompt engineering, decomposition pipelines, or entity-level intermediate representations to achieve strong performance. |
| Approach: | They propose a diagnostic benchmark for long-context tabular summarization using decomposition pipelines and entity-level intermediate representations. |
| Outcome: | The proposed benchmark improves accuracy and numerical fidelity, but lacks local arithmetic. |