AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training

Christian Moya, Alex Semendinger, Guang Lin, Elliott Thornley

ICML 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Causal approaches to fairness · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add informative tie training (equal-utility pairs with differing spurious features) to DPODPO on synthetic hotel preferences · Hotel preferences, adversarial shift (Qadv)pairwise accuracy (%): 64.20% -> 86.70%Improved
add informative tie training to DPODPO on synthetic hotel preferences · Hotel preferences, suppressed correlation (Qsup)pairwise accuracy (%): 74.00% -> 82.85%Improved
add informative tie training to DPODPO on synthetic hotel preferences · Hotel preferences, in-distribution (P)pairwise accuracy (%): 92.25% -> 92.40%No clear effect
add tie training (alpha = 0.75) to DPO on an MLP scorerDPO with MLP scorer on synthetic features · Neural network adversarial accuracyadversarial accuracy: ≈0.25 -> ≈0.7Improved
add tie training (alpha = 0.75) to DPO on an MLP scorerDPO with MLP scorer on synthetic features · Neural network spurious gapspurious gap (aligned minus misaligned accuracy): ≈0.7 -> ≈0.45Improved
increase fraction of strict preferences (reduce tie mixing) (ablation)tie training MLP scorer · Neural network spurious gapspurious gapHurt
increase training sample size n under strict DPO (ablation)strict DPO on log-linear model · Linear deployment suboptimalitydeployment suboptimalityNo clear effect
increase training samples under strict DPO (ablation)strict DPO on MLP scorer · Neural network adversarial accuracyadversarial accuracyNo clear effect
use ties at small sample size (ablation)tie training MLP scorer · Neural network small nadversarial accuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy