5 papers · 1 filter
Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models
Saksham Khatwani, He Cheng, Majid Afshar +2
Biomedical knowledge graphs (KGs) offer structured medical knowledge that can ground large language model (LLM) reasoning in clinical diagnosis application, yet how KG signal shoul…
Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
Dananjay Srinivas, Saksham Khatwani, Maria Pacheco
When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We frame this…
LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval
He Cheng, Yifu Wu, Saksham Khatwani +5
Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in this integration is multi-hop…
Enhancing Structured Meaning Representations with Aspect Classification
Claire Benét Post, Paul Bontempo, August Milliken +6
To fully capture the meaning of a sentence, semantic representations should encode aspect, which describes the internal temporal structure of events. In graph-based meaning represe…
Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning
Saksham Khatwani, He Cheng, Majid Afshar +2
Large language models (LLMs) show promise for diagnostic reasoning but often lack reliable, knowledge grounded inference. Knowledge graphs (KGs), such as the Unified Medical Langua…