vrr/WFGY
2
0
Fork 0
mirror of https://github.com/onestardao/WFGY.git synced 2026-04-29 12:10:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Update multi-hop-collapse.md

Browse source
This commit is contained in:
PSBigBig 2025-09-05 11:30:32 +08:00 • committed by GitHub
parent 53c8dbe751
commit 3a06934d30
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 17 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

17
ProblemMap/GlobalFixMap/Multimodal_LongContext/multi-hop-collapse.md
View file

@ -1,5 +1,22 @@
# Multi-Hop Collapse — Multimodal Long Context
<details>
<summary><strong>🧭 Quick Return to Map</strong></summary>
<br>
> You are in a sub-page of **Multimodal_LongContext**.
> To reorient, go back here:
>
> - [**Multimodal_LongContext** — long-context reasoning across text, vision, and audio](./README.md)
> - [**WFGY Global Fix Map** — main Emergency Room, 300+ structured fixes](../README.md)
> - [**WFGY Problem Map 1.0** — 16 reproducible failure modes](../../README.md)
>
> Think of this page as a desk within a ward.
> If you need the full triage and all prescriptions, return to the Emergency Room lobby.
</details>
When reasoning requires **multi-hop steps across modalities** (e.g., text → image → audio → video),
the chain often collapses midway. The model answers only the first hop or fabricates the rest,
losing alignment between evidence sources.