1-010-counterfactual-edits-rooted-chinese-cultural-entities-aligned CLM-0282observationsingle paperReviewed by AI
On 1,010 counterfactual edits rooted in Chinese cultural entities and aligned with English counterparts, an edit made in one language largely does not propagate to the other: edits succeed in the edited language (about 80% for Chinese at batch size 10, falling with batch size) while the other language keeps answering the old fact, so multilingual models store the same fact in language-specific ways that editing does not bridge.
Capability: Absorbing and flexibly using new knowledge
Observed on
CLM-Bench, Llama-3 and Qwen2 among others, 2026; batches of 10, 100 and 1000 edits; Chinese-first construction rather than translated English data..
Sources
- supportsCLM-Bench: Benchmarking and Analyzing Cross-lingual Misalignment of LLMs in Knowledge EditingTwo languages only; the culturally native construction avoids the translation artefact the authors criticize in prior multilingual editing benchmarks.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- In a two-agent extract-then-answer pipeline on multilingual extractive QA, routing the inter-agent handoff through English (forward-translate facts, answer in English, back-translate) lowers Exact Match relative to keeping handoffs in the user's language, and the loss grows with distance from English (13.0 points Spanish up to 30.6 points Hindi with Aya-23-8B).Getting more from several models than from one · reviewed by AI
- Knowledge-editing methods such as ROME and fine-tuning insert a stated fact reliably but do not carry its logical consequences: on multi-hop questions generated from knowledge-graph rules that the edit entails, accuracy is up to 24 points lower than on the directly edited fact, so an edited model can assert a new fact and still answer as if its implications never changed.Absorbing and flexibly using new knowledge · reviewed by AI
- A single fact edit exerts two coupled pressures on its knowledge neighbourhood, propagation to facts that should change and leakage into facts that should not, and planning the edit's target representations jointly under both constraints, with a gate that rejects risky plans before touching parameters, improved propagation and preservation on RippleEdits by at least 7% across backbones over methods that treat the two separately.Absorbing and flexibly using new knowledge · reviewed by AI
- When instruction-tuned models (Qwen2.5 7B-32B) make function calls from non-English user requests, they often select the right tool and argument names but emit argument values in the wrong language, a failure that exact-match or AST tool-calling metrics record as a generic invocation error rather than a language mismatch.Using the tools it is given · reviewed by AI
- On paired solvable/unsolvable math problems translated into French and Greek, natively multilingual models (Gemma-4-31B, Qwen3-4B/30B) encode solvability most sharply in English yet agree least with that internal belief in their stated verdict in English, being more faithful in the lower-resource languages, while a weakly multilingual model (Llama-3.1-8B) shows the opposite ordering.Saying what actually drove the answer · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: An editing method whose cross-lingual success matches in-language success on CLM-Bench.