elias/core
1
0
Fork 0
mirror of https://github.com/eliasstepanik/core.git synced 2026-01-12 00:18:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Manik Aggarwal 2025-10-01 21:41:16 +05:30 committed by GitHub
parent f539ad1ecd
commit dc9b149445
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -48,7 +48,7 @@
## 🔥 Research Highlights ## 🔥 Research Highlights
CORE memory achieves **88.24%** average accuracy in Locomo dataset across all reasoning tasks, significantly outperforming other memory providers. Check out this [blog](https://blog.heysol.ai/we-built-memory-for-individuals-and-achieved-sota-on-locomo-benchmark/) for more info. CORE memory achieves **88.24%** average accuracy in Locomo dataset across all reasoning tasks, significantly outperforming other memory providers. Check out this [blog](https://blog.heysol.ai/core-build-memory-knowledge-graph-for-individuals-and-achieved-sota-on-locomo-benchmark/) for more info.
<img width="6048" height="3428" alt="benchmark" src="https://github.com/user-attachments/assets/2e5fdac5-02ed-4d00-9312-c21d09974e1f" /> <img width="6048" height="3428" alt="benchmark" src="https://github.com/user-attachments/assets/2e5fdac5-02ed-4d00-9312-c21d09974e1f" />
(1) Single-hop questions require answers based on a single session; (2) Multi-hop questions require synthesizing information from multiple different sessions; (3) Open-domain knowledge questions can be answered by integrating a speaker’s provided information with external knowledge such as commonsense or world facts; (4) Temporal reasoning questions can be answered through temporal reasoning and capturing time-related data cues within the conversation; (1) Single-hop questions require answers based on a single session; (2) Multi-hop questions require synthesizing information from multiple different sessions; (3) Open-domain knowledge questions can be answered by integrating a speaker’s provided information with external knowledge such as commonsense or world facts; (4) Temporal reasoning questions can be answered through temporal reasoning and capturing time-related data cues within the conversation;
@ -220,3 +220,4 @@ Have questions or feedback? We're here to help: