Papers by Srinivasan Parthasarathy
(CPER) From Guessing to Asking: An Approach to Resolving Persona Knowledge Gap in LLMs during Multi-Turn Conversations (2025.naacl-srw)
Copied to clipboard
| Challenge: | Existing methods for identifying and resolving persona knowledge gaps are underexplored. |
| Approach: | They propose a framework that dynamically detects and resolves persona knowledge gaps using intrinsic uncertainty quantification and feedback-driven refinement. |
| Outcome: | The proposed framework detects and resolves persona knowledge gaps using intrinsic uncertainty quantification and feedback-driven refinement on two real-world datasets: CCPE-M for preferential movie recommendations and ESConv for mental health support. |
SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis (2021.emnlp-main)
Copied to clipboard
| Challenge: | Crypto markets are forums where goods and services are exchanged between parties who use encryption to conceal their identities. |
| Approach: | They propose a stylometry-based multitask learning approach for natural language and model interactions using graph embeddings. |
| Outcome: | The proposed approach outperforms existing methods in four darknet forums with a lift of up to 2.5X on the mean retrieval rank and 2X on recall@10. |
Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths (2020.coling-main)
Copied to clipboard
| Challenge: | Abstractive summarization at controllable lengths is a challenging task in natural language processing . high variance in screen-sizes often require extensive human supervision to perform these modifications. |
| Approach: | They propose a supervised method to construct abstractive summaries of a text document at controllable lengths using an interpretable multi-headed attention mechanism. |
| Outcome: | The proposed method outperforms baselines on two low-resource datasets in English by 14.70%. |