Bradley-Terry Training Can Distort Outcome Probabilities of Initially Accurate Language World Models
원문 초록
Comparative feedback, in which a judge says which of two candidate outcomes is closer to what happened, is a practical way to train language world models that assign probabilities to an action's outcomes. We show that, fitted with a Bradley-Terry objective, it need not teach the true outcome probabilities and can distort accurate ones. On a simulated robot push with enumerated outcome distributions, this objective takes a model that is accurate on unseen layouts (hazard error 2.4 percentage points, pp) and moves 33 to 43 pp of its probability onto outcomes that none of a condition's enumerated branches produces. The cause is the objective, not the comparisons: its optimum, computed before training, predicts where the model ends up, and a likelihood that knows the judge's rule learns from the same comparisons without the shift. The shift is robust: it recurs on unseen conditions, under five candidate laws and a three-fold denser enumeration, and about 29 pp remain without the physically impossible events. Its cost is conditional: with those events it inflates hazard probabilities, and a threshold inherited from the pre-feedback model costs about 3 pp of utility per decision on trained and 1 to 2 pp on unseen conditions, through false rejects; without them the utility loss averages below 1 pp over six seeds, though a small regret in action choice remains. Audits of readout, response and decision trace the effect from probabilities to actions.
제출 이력
확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.
- arXiv:2611.25594v1제출 시각 미확인
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
공통 태그로 연결된 공개 논문이 아직 없습니다.
토론
이 논문과 연결된 포럼 글이 아직 없습니다.