Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models
Language models may encode both outdated facts and their newer replacements. We introduce Parametric Temporal Conflict (PTC), where the newer fact is present and recoverable, but the default forward pass prefers the outdated one. We release a deterministically verified benchmark of 8,746 Wikidata position-holder transitions and evaluate four open-weight language models across three families. A date-prefix prompt recovers the newer fact in 61-81% of PTC cases. Activation patching flips predictions in 72-85% of cases and localizes the preference to model-specific upper-layer regions. Residual-stream steering outperforms norm-matched random directions, indicating direction-specific represent...
| Authors | Elias Hossain, Sourav Saha, Tasfia Nuzhat Ornee et al. |
|---|---|
| Primary category | cs.LG |
| Published | 18 June 2026 |
| Last updated at source | 5 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.