What is recorded here?
Trains linear hidden-state classifiers against binarized semantic-entropy targets, estimating uncertainty from one generation instead of repeated test-time sampling.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Requires hidden-state access and sampling-based training targets; low test-time overhead does not remove training cost. Before-generation and end-of-generation locations differ. Source v1 discrete-probability paragraph appears to divide sample counts by cluster count K rather than sample count N; implementation/formula reconciliation not independently replayed. No universal truth guarantee or biological application claim.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Jannik Kossen; Jiatong Han; Muhammed Razzak; Lisa Schut; Shreshth Malik; Yarin Gal
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
Trains linear hidden-state classifiers against binarized semantic-entropy targets, estimating uncertainty from one generation instead of repeated test-time sampling.
Scientific scope
Requires hidden-state access and sampling-based training targets; low test-time overhead does not remove training cost. Before-generation and end-of-generation locations differ. Source v1 discrete-probability paragraph appears to divide sample counts by cluster count K rather than sample count N; implementation/formula reconciliation not independently replayed. No universal truth guarantee or biological application claim.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Jannik Kossen; Jiatong Han; Muhammed Razzak; Lisa Schut; Shreshth Malik; Yarin Gal
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.