[KongchangAI]
Model

MedGraph

A graph-memory-based memory system for LLM medical dialogue. By constructing fact chains with timestamps and person attribution, it reads states at the time point of a question during retrieval, addressing state tracking, person attribution, and safe fact recall in long-term medical conversations.

Timeline (last 90 days)

Nov 6

MedGraph builds graph memory that links facts into chains by date and person attribution, and reads them at the time point of the question during retrieval.

Unverified50%
Nov 6

On the MedMemoryBench benchmark, MedGraph with a GPT backbone achieves the highest overall accuracy, leading the strongest baseline by 10.5 percentage points.

Unverified50%
Nov 6

On the MedMemoryBench benchmark, MedGraph with a Qwen backbone achieves the highest overall accuracy, leading the strongest baseline by 10.4 percentage points.

Unverified50%
Nov 6

Under the GPT setting, MedGraph's memory construction and answering efficiency are also relatively high.

Unverified50%
Nov 6

MedGraph's patient profile lists all recorded safety facts and associates them with each question.

Unverified50%

All Facts (5)

Source Articles