Danush Khanna

4 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14)

Venues

ACL (3) EMNLP (1)

Top co-authors

Gurpreet Singh (2) Vinija Jain (2) Amitava Das (2) Aman Chadha (2) Kripabandhu Ghosh (2) Vasu Sharma (2) Jyoti Patel (1) Utkarsh Bhatt (1) Shubham Singh (1) Chhavi Sharma (1)

Research topics

Artificial Intelligence (4) Core AI (4) Machine Learning (3) Natural Language Processing (3) Core Methods (3) Deep Learning (2) Applications (2) Models (2) Resources & Methods (2) Interdisciplinary (1) Optimization & Theory (1) Social (1)

Keywords

large language model (3) direct preference optimization (1) preference alignment (1) natural language inference (1) prompt engineering (1) explanation generation (1) semantic alignment (1) instruction tuning (1) kullback-leibler divergence (1) prompting strategy (1) divergence measure (1) alignment quality (1) jailbreak detection (1) legal text classification (1) legal judgment prediction (1) layer-wise pooling (1) kernel methods (1) transformer model (1) mental manipulation detection (1) multi-person dialogue (1)

Papers

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations EMNLP 2025 DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization ACL 2025 SELF-PERCEPT: Introspection Improves Large Language Models’ Detection of Multi-Person Mental Manipulation in Conversations ACL 2025 Legal Judgment Reimagined: PredEx and the Rise of Intelligent AI Interpretation in Indian Courts ACL 2024