Papers by Srinivasan H. Sengamedu
Disentangling Biased Knowledge from Reasoning in Large Language Models via Machine Unlearning (2025.acl-long)
Copied to clipboard
Zheyuan Liu, Suraj Maharjan, Fanyou Wu, Rahil Parikh, Belhassen Bayar, Srinivasan H. Sengamedu, Meng Jiang
| Challenge: | Existing approaches to disentangle biased knowledge from reasoning are sub-optimal . entangled data makes curation difficult, leading to inclusion of sensitive, toxic data. |
| Approach: | They propose a framework that selectively removes biased knowledge while preserving reasoning abilities. |
| Outcome: | The proposed framework improves fairness accuracy by 14.7% and reasoning performance by 62.6% across multiple LLMs. |
Feedback-Aware Prompt Optimization Framework for Generating Job Postings (2026.eacl-industry)
Copied to clipboard
| Challenge: | Creating high-quality job postings is time-consuming and requires significant time from hiring managers and recruiters. |
| Approach: | They propose a feedback-aware prompt optimization framework that automates high-quality job posting generation through iterative human-in-the-loop refinement. |
| Outcome: | The proposed framework shows high compliance rates and strong satisfaction scores in both automated and human evaluations. |
Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning (2026.eacl-long)
Copied to clipboard
| Challenge: | scalability challenges arise as conversations extend over weeks or months . current approaches fragment conversations into isolated embeddings or graph representations . |
| Approach: | They propose a working memory framework that actively constructs structured memory representations . the framework organizes conversational fragments into episodic narratives based on momentum . |
| Outcome: | Amory improves performance on LOCOMO benchmark while reducing response time by 50%. |