Papers by Roshan Santhosh
Decomposition-Enhanced Training for Post-Hoc Attributions in Language Models (2026.eacl-long)
Copied to clipboard
Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami, Ryan A. Rossi, Varun Manjunatha, Roshan Santhosh, Ruiyi Zhang, Soheil Feizi, Nedim Lipka
| Challenge: | Existing methods for extractive QA struggle in multi-hop, abstractive, and semi-extractive settings. |
| Approach: | They propose a method that prompts models to produce answer decompositions as intermediate reasoning steps. |
| Outcome: | The proposed method outperforms existing methods and matches or exceeds state-of-the-art frontier models. |
Inducing Generalizable and Interpretable Lexica (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Lexica are widely used as generalizable language features to predict sentiment, emotions, mental health, and personality. |
| Approach: | They propose to induce lexica using context-oblivious and context-aware approaches and compare their performance using crowd-worker assessment. |
| Outcome: | The proposed models can be induced using context-oblivious and context-aware approaches and evaluate their quality using crowd-worker assessment. |