RESEARCHMonitorWATCHLIST
What Breaks and What Comes Back: Capability Damage and Recovery in Depth-Pruned Small Language Models
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers analyzed depth pruning and fine-tuning recovery across four 1.2-1.7B parameter models for agentic capabilities.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 4 November 2026
- Collected by OneBench
- 5 Nov 2026, 02:01 UK
Stored source excerpt
arXiv:2611.00877v1 Announce Type: new Abstract: Depth pruning removes whole Transformer blocks to make a language model smaller and faster, but the damage is not spread…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.