Papers by Anubhav Sinha
Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for text classification using autoregressive language models are limited . authors propose a novel technique for text classification using autoreregressives . |
| Approach: | They propose a two-step technique for text classification using autoregressive language models . they use a set of perplexity and log-likelihood based numeric features to elicit a text instance . |
| Outcome: | The proposed technique eliminates parameter updates in LMs and does not limit training examples . it is evaluated across 5 datasets and compares with multiple competent baselines . |
Unintended Bias Detection and Mitigation in Misogynous Memes (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing models that detect misogyny are not able to detect unintended biases in memes, perpetuating harmful stereotypes and reinforcing negative attitudes. |
| Approach: | They propose to measure and mitigate unintentional bias in misogynous memes detection models by using a contextualized scene graph-based multimodal network (CTXSGMNet) they also evaluate their generalizability by evaluating their performance on a few benchmark meme datasets. |
| Outcome: | The proposed model achieves state-of-the-art performance on the SemEval-2022 Task 5 (MAMI task) dataset, showcasing its promising performance in terms of Equity of Odds and F1 score. |
Argumentation and Judgement Factors: LLM-based Discovery and Application in Insurance Disputes (2026.eacl-long)
Copied to clipboard
| Challenge: | In this paper, we focus on finding legal factors for a specific case type under consideration . we propose a multi-step approach for discovering a list of AJFs for . a given case type. |
| Approach: | They propose a multi-step approach for discovering a list of AJFs for a given case type . they construct and evaluate the discovered list on two different types of cases . |
| Outcome: | The proposed approach is based on a set of relevant legal documents and a large-scale LLM. |