SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
SARA is a unified RAG framework that balances local factual precision with global coverage by combining natural-language spans with compact semantic compression vectors, achieving consistent gains under strict context budgets.
Jul 1, 2026
Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations
A systematic study showing that reasoning capabilities alone are insufficient for LLMs in multi-turn mental health conversations, isolating failure modes that demand additional safety and empathy-aware design.
Jul 1, 2026
MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models
MedHalu is a fine-grained benchmark for studying hallucinations in LLM responses to consumer healthcare queries, analyzing hallucination patterns across models, query types, and medical specialties.
Jun 1, 2026
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
UniSD unifies the fragmented landscape of self-distillation for large language models, providing a principled framework that supports systematic comparison and new combinations across data, representation, and decoding levels.
May 30, 2026
UniSD
A unified self-distillation framework for large language models that consolidates fragmented self-distillation directions into a single, modular formulation across data, representation, and decoding levels. Under review at NeurIPS 2026.
May 30, 2026
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
TextReg introduces a regularized text-space optimization objective that mitigates prompt distributional overfitting, improving robustness across tasks, models, and evaluation distributions.
May 30, 2026
Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
Sysformer learns adaptive, query-conditioned system prompts to safeguard frozen large language models, providing fine-grained safety control without modifying model weights.
Apr 23, 2026
Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models
Sharpness-aware prompt evolution optimizes prompts for both performance and robustness by penalizing sharp regions in the prompt loss landscape, yielding prompts that transfer better across tasks and LLM families.
Apr 23, 2026
SARA
Selective and Adaptive Retrieval-augmented Generation with Context Compression. A unified RAG framework that combines fine-grained natural-language spans with compact semantic compression vectors under strict context budgets. Accepted at ACL 2026 main conference.
Mar 15, 2026
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
We introduce SlideAgent, a versatile agentic framework for understanding multi-modal, multi-page, and multi-layout documents.
Nov 27, 2025