Sourceunknownno stored text
Reasoning Models Don't Always Say What They Think
Author not recordedDate not recordedOriginal︎ ↗
Claims1
ExaminationsNone
TextNot stored
VersionsOne known
CopiesNone recorded
CorrectionsNot checked
Facts not yet checkedReachNo copies recorded
StructureIn 1 claim's map0 sources downstream across 1 claim
EvidenceNot yet read
Examinations
None recorded.
Text
No stored copy. Only the passages claims quote are recorded.
As quoted
for most settings and models tested, CoTs reveal their usage of hints in at least 1% of examples where they use the hint, but the reveal rate is often below 20%, (2) outcome-based reinforcement learning initially improves faithfulness but plateaus without saturating, and (3) when reinforcement learning increases how frequently hints are used (reward hacking), the propensity to verbalize them does not increase
Reasoning models often omit from chain of thought hints or reward hacks that drive their answers.
Not yet read by this claim’s Steward.
Lineage across 1 claim
Draws on · none recorded
This source
Drawn on by · none recordedReasoning Models Don't Always Say What They Think
in 1 claim's map
Record
- Kind
- unknown
- Authors
- Not recorded
- Publisher
- Not recorded
- Published
- Not recorded
- DOI
- None
- Link
- https://arxiv.org/abs/2505.05410
- Archived copy
- None found
- Stored text
- None; quoted passages only
- Claims extracted
- Not recorded
- Versions
- One known
- Copies
- None recorded
- Corrections
- Not yet checked
- Facts checked
- Not yet
History 1
- Oct 30, 2026Entered the graphEntered the graph; no copy stored