phuongntc commited on
Commit
c709566
·
verified ·
1 Parent(s): 5c31450

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -8
README.md CHANGED
@@ -242,14 +242,6 @@ We construct a calibrated dataset of **80,856** labeled *(document, summary)* pa
242
  - Reward modeling for PPO/GRPO-style fine-tuning and iterative data curation
243
 
244
  ---
245
-
246
- ## Limitations
247
- - **Context truncation** may omit relevant evidence for long documents.
248
- - **Domain shift** can reduce reliability (especially relevance/content-centrality).
249
- - Scores are **proxy estimates** of human judgment; validate in downstream loops to mitigate reward hacking.
250
-
251
- ---
252
-
253
  ## Reproducibility & version pinning
254
 
255
  Pin a specific revision/commit when reproducing paper results:
 
242
  - Reward modeling for PPO/GRPO-style fine-tuning and iterative data curation
243
 
244
  ---
 
 
 
 
 
 
 
 
245
  ## Reproducibility & version pinning
246
 
247
  Pin a specific revision/commit when reproducing paper results: