Papers by Anil Bandhakavi
CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Current evaluation methods do not capture complex attributes of counterspeech quality, such as contextual relevance, aggressiveness, or argumentative coherence. |
| Approach: | They propose to use a dataset and framework to evaluate counterspeech quality across four dimensions: contextual relevance, aggressiveness, argument-coherence, and suitability. |
| Outcome: | The proposed method outperforms ROUGE, METEOR, and BertScore in correlating with human judgement, indicating a significant improvement in automated counterspeech evaluation. |
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. |
Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to generate counterspeech based on intents are limited to single attributed . however, a holistic approach that considers multiple attributes simultaneously yields more nuanced and effective responses. |
| Approach: | They propose a framework that leverages hierarchical prefix learning with preference optimization to generate more constructive counterspeech. |
| Outcome: | The proposed framework improves intent conformity and emotion labels in 13,973 counterspeech instances. |
Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing systems that target hate speech with intent-conditioned counterspeech generate better results with longer contexts. |
| Approach: | They propose a framework that enables counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. |
| Outcome: | The proposed framework outperforms existing benchmarks in intent-conditioned counterspeech generation. |