EditRisk-Bench demonstrates that malicious knowledge editing reliably induces incorrect or unsafe reasoning in LLMs while largely preserving general capabilities.
The butterfly effect of model editing: Few edits can trigger large language models collapse
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing
EditRisk-Bench demonstrates that malicious knowledge editing reliably induces incorrect or unsafe reasoning in LLMs while largely preserving general capabilities.