Track reproducing *Factual Self-Awareness in Language Models* as a canonical Murano usage example on UKP Lab's own published work. **Paper:** https://arxiv.org/abs/2505.21399 **Authors:** Hovhannes Tamoyan (@tamohannes), Subhabrata Dutta (@Subha0009), Iryna Gurevych **Reference implementation:** https://github.com/UKPLab/arxiv2025-self-awareness ## Scope - Reproduce the linear-probe analysis on residual-stream activations for known / forgotten factual recall using the post-refactor `Pipeline` + `Probe` API. - Optionally reproduce the SAE comparison from the paper (depends on SAE support being ported back; tracked in #58). - Ship a runnable example under `examples/use_cases/` (or equivalent) plus a reproductions entry in the docs site. ## Dependencies - SAE port (tracked in #58): if it lands, this reproduction includes the SAE analysis; otherwise it's linear-probe only. ## Ownership Owner TBD. Any co-author with access to the external repo can pick this up. Not 0.1.0-blocking.
Track reproducing Factual Self-Awareness in Language Models as a canonical Murano usage example on UKP Lab's own published work.
Paper: https://arxiv.org/abs/2505.21399
Authors: Hovhannes Tamoyan (@tamohannes), Subhabrata Dutta (@Subha0009), Iryna Gurevych
Reference implementation: https://github.com/UKPLab/arxiv2025-self-awareness
Scope
Pipeline+ProbeAPI.examples/use_cases/(or equivalent) plus a reproductions entry in the docs site.Dependencies
Ownership
Owner TBD. Any co-author with access to the external repo can pick this up. Not 0.1.0-blocking.