AI Paper Atlas

Research map / Large language models / Alignment and preferences

RankList – a Listwise Preference Learning Framework for Predicting Subjective Preferences

Abinay Reddy Naini, Fernando Diaz, Carlos Busso

AAAI 2026 · Large language models › Alignment and preferences · approach: Robust and calibrated DPO · 3 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 log-sum-exp approximation instead of exact sum of pairwise log losses (ablation)RankList · MSP-Podcast arousalKendall's Tau: 0.564 -> 0.591Improved
add log-sum-exp approximation instead of exact sum of pairwise log losses (ablation)RankList · MSP-Podcast dominanceKendall's Tau: 0.430 -> 0.461Improved
add skip-term comparisons to adjacent-only loss (ablation)RankList · MSP-Podcast arousalKendall's Tau: 0.571 -> 0.591Improved
add skip-term comparisons to adjacent-only loss (ablation)RankList · MSP-Podcast dominanceKendall's Tau: 0.442 -> 0.461Improved
extend skip comparisons from skip-2 to skip-3 (ablation)RankList · MSP-Podcast arousalKendall's Tau: 0.591 -> 0.580No clear effect
reduce skip comparisons from skip-2 to skip-1 (ablation)RankList · MSP-Podcast arousalKendall's Tau: 0.591 -> 0.586No clear effect
add RankNet pairwise pre-training before listwise loss (ablation)RankList · MSP-Podcast dominanceKendall's Tau: 0.439 -> 0.461Improved
add RankNet pairwise pre-training before listwise loss (ablation)RankList · MSP-Podcast arousalKendall's Tau: 0.582 -> 0.591Improved
use listwise RankList instead of pairwise RankNetRankNet · MSP-Podcast arousalKendall's Tau: 0.526 -> 0.591Improved
use RankList instead of RnC on IEMOCAP dominance within-corpusRnC · IEMOCAP dominance (within-corpus)Kendall's Tau: 0.370 -> 0.372No clear effect
vary minimum score margin W for list construction (ablation)RankList · MSP-PodcastKendall's TauMixed
increase training size with matched visible comparisons, listwise versus pairwiseRankList · MSP-Podcast arousalKendall's TauImproved

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