@yoheinakajima: longmemeval experiment arch: 1) deterministic ingestion/extraction (85.6% accuracy, 86.2% retrieval) 2) semantic ingest…

X AI KOLs Timeline Papers

Summary

The tweet shares results from LongMemEval experiments comparing deterministic and semantic ingestion/extraction methods, achieving up to 87.6% accuracy and 90.0% retrieval with a hybrid approach.

longmemeval experiment arch: 1) deterministic ingestion/extraction (85.6% accuracy, 86.2% retrieval) 2) semantic ingestion/extraction (84.8% accuracy, 94.9% retention) 3) semantic ingestion/deterministic extraction (87.6% accuracy, 90.0% retrieval) this was staggered, not
Original Article
View Cached Full Text

Cached at: 06/01/26, 05:47 PM

longmemeval experiment arch:

  1. deterministic ingestion/extraction (85.6% accuracy, 86.2% retrieval)
  2. semantic ingestion/extraction (84.8% accuracy, 94.9% retention)
  3. semantic ingestion/deterministic extraction (87.6% accuracy, 90.0% retrieval)

this was staggered, not

ActiveGraph (@ActiveGraphAI): Our third LongMemEval experiments by adding semantic ingestion to deterministic retrieval.

The hybrid approach improved end-to-end QA accuracy to 87.6% and evidence retrieval to 90.0%, but the QA gain did not reach statistical significance in this run.

Similar Articles