Papers by Punyajoy Saha
HateCheckHIn: Evaluating Hindi Hate Speech Detection Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Hate speech detection models are evaluated on a held-out test data, but they are incapable of identifying weaknesses. |
| Approach: | They propose to use multilingual hate speech detection models to evaluate their performance on social media conversation. |
| Outcome: | The proposed model can detect hate speech in multiple languages using a real-world conversation on social media. |
InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks (2024.lrec-main)
Copied to clipboard
| Challenge: | InfFeed uses influence functions to compute the influential instances for a target instance. |
| Approach: | They propose an apparatus that uses influence functions to compute the influential instances for a target instance. |
| Outcome: | The proposed model outperforms the state-of-the-art baselines by 4% for hate speech classification, 3.5% for stance classification, and 3% for irony and 2% for sarcasm detection. |
HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation (2025.findings-acl)
Copied to clipboard
Naquee Rizwan, Seid Muhie Yimam, Daryna Dementieva, Dr. Florian Skupin, Tim Fischer, Daniil Moskovskiy, Aarushi Ajay Borkar, Robert Geislinger, Punyajoy Saha, Sarthak Roy, Martin Semmann, Alexander Panchenko, Chris Biemann, Animesh Mukherjee
| Challenge: | Existing approaches to manage hate speech rely on reactive measures such as blocking or suspending offensive messages . despite regulations imposed by nations and social media platforms, hateful content remains a challenge . |
| Approach: | They propose a framework for automated hate speech moderation based on different strategies . they examine hate speech regulations and strategies from three perspectives . |
| Outcome: | The proposed framework could be based on a combination of country regulations, social platform policies, and NLP research datasets. |
Probing LLMs for hate speech detection: strengths and vulnerabilities (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent efforts to detect hateful or toxic language using large language models have not used explanation, additional context and victim community information in the detection process. |
| Approach: | They use different prompt variations, input information and victim community information to evaluate large language models in zero shot setting without adding any in-context examples. |
| Outcome: | The proposed models perform significantly better when included in the pipeline than baseline models. |
On Zero-Shot Counterspeech Generation by LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used in numerous NLP tasks, including counterspeech generation. |
| Approach: | They propose three different prompting strategies for generating different types of counterspeech and propose a set of prompting techniques for counterspeak generation. |
| Outcome: | The proposed prompting strategies improve the performance of the models for counterspeech generation in two datasets, but with high toxicity with increase in model size. |
Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi (2024.findings-eacl)
Copied to clipboard
| Challenge: | NLP is a technique that generates counterspeech that “counters” the vicious tone of online abuse and dilutes/ameliorates their rippling effect over the social network. |
| Approach: | They propose to use neural architectures to generate counterspeech that can "counter" the vicious tone of online abuse and dilute/ameliorate their rippling effect over the social network. |
| Outcome: | The proposed model can generate counterspeech in monolingual setups and is more transferable when languages belong to the same language family. |
Hate Speech and Offensive Language Detection in Bengali (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing research on hate speech detection in English does not cover low-resource languages like Bengali. |
| Approach: | They develop an annotated dataset of 10K Bengali posts consisting of 5K actual and 5K Romanized Bengali tweets. |
| Outcome: | The proposed model outperforms other models on training actual and romanized datasets by interpreting the semantic expressions better. |