Unverified50% confidenceFactExact time
The paired test revealed a systematic bias: some models claim that a better alternative exists regardless of whether the optimal plan has already been provided.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/5/2026
First Seen
Valid until: 2/3/2027
Sources
Related Entities
Related Claims
UnverifiedThe study recommends that rather than pursuing a single perfect reward, one should systematically anticipate and test shortcuts the model might exploit, and incorporate adversarial validation into the design phase.76% similarUnverifiedChanging the candidate should be a later experimental option, not the default reaction to all failures.75% similarUnverifiedEven when two models have similar accuracy, the ways they solve problems and their reasoning paths may differ substantially, and this strategic diversity is one source of the value of heterogeneous teams.74% similarUnverifiedThe "consistently producing stronger claims" observed in the experiments is not an incidental bias of some particular model, but a structural tendency of agentic workflows.73% similarUnverifiedThe evaluation of large models should go beyond the multiple-choice paradigm; testing only whether correct answers are selected is insufficient to measure genuine factual understanding, and adversarial evaluation that tests rejection of incorrect statements must be introduced.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1137709API
curl https://kongchang.com/api/v1/knowledge/claims/1137709MCP
get_claim(id=1137709)