Papers by Aseem Srivastava
Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit remarkable capabilities in various generative tasks, but their adaptation to domain-specific intricacies remains challenging. |
| Approach: | They propose to use a planning engine to orchestrate structuring knowledge alignment to achieve high-order planning by encapsulating domain knowledge and leveraging sheaf convolution learning to enhance its understanding of the dialogue’s structural nuances. |
| Outcome: | The proposed framework improves on existing LLMs and shows that it can generate better summaries with better quality and better execution. |
Assess and Prompt: A Generative RL Framework for Improving Engagement in Online Mental Health Communities (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical results across four notable language models demonstrate significant improvements in attribute elicitation and user engagement. |
| Approach: | They propose a framework that identifies and prompts users to enrich their posts by eliciting missing support attributes. |
| Outcome: | The proposed framework improves engagement and elicits missing information from posts. |
Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent systems exhibit conversational competence but lack structured mechanisms to evaluate adherence to core therapeutic principles. |
| Approach: | They propose a framework to evaluate therapist-like responses for clinically grounded appropriateness and effectiveness using an ordinal scale. |
| Outcome: | The proposed framework achieves an F-1 score of 63.34 versus the baseline Qwen3 score of 38.56 . |