Papers by Aakash Kumar
A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing approaches to extract actionable suggestions from customer reviews are often mixed-intent, unstructured text. |
| Approach: | They propose a hybrid pipeline that uses a RoBERTa classifier and a precision–recall surrogate to extract actionable suggestions from customer reviews. |
| Outcome: | The proposed pipeline outperforms prompt-only, rule-based, and classifier-only baselines in extraction accuracy and cluster coherence. |
Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Specifically, we tried native sample mixing, multi-task learning, and prompting and instruction finetuning very large multilingual language models (VMLMs). |
| Approach: | They used native sample mixing, multi-task learning and prompting and instruction finetuning to improve code-mixed humour and sarcasm detection. |
| Outcome: | The proposed methods improve humour and sarcasm detection by adding native samples to training sets and multitask learning and prompting and instruction finetuning VMLMs. |