AI Paper Atlas

Research map / Large language models / Alignment and preferences

Supporting High-Stakes Decision Making Through Interactive Preference Elicitation in the Latent Space

Michael Eichelbeck, Tim Voigt, Matthias Althoff

ICLR 2026 · Large language models › Alignment and preferences · approach: Reward model design and preference models

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
run PBO in the autoencoder latent space with probabilistic LLM prior, versus vanilla PBOPBO · Idealista18 Madrid (LLM simulation)pairwise accuracy: 0.539 -> 0.613Improved
run PBO in the autoencoder latent space with probabilistic LLM prior, versus vanilla PBOPBO · Idealista18 Madrid (LLM simulation)NDCG@10: 0.622 -> 0.706Improved
add autoencoder latent space with static prior to PBOPBO · Idealista18 Madrid (statistical simulation)pairwise accuracy: 0.510 -> 0.556Improved
add autoencoder latent space with static prior to PBOPBO · Idealista18 Madrid (statistical simulation)NDCG@10: 0.658 -> 0.584Hurt
add probabilistic LLM prior instead of direct LLM weight prior (ablation)PBO+AE · Idealista18 Madridpairwise accuracy: 0.488 -> 0.613Improved
add probabilistic LLM prior instead of static prior (ablation)PBO+AE · Idealista18 Madridpairwise accuracy: 0.605 -> 0.613Improved
add probabilistic LLM prior instead of static prior (ablation)PBO+AE · Idealista18 MadridNDCG@10: 0.685 -> 0.706Improved
add LLM-driven direct weight specification instead of static prior (ablation)PBO+AE · Idealista18 Madridpairwise accuracy: 0.605 -> 0.488Hurt
add probabilistic LLM prior on Munich dataset instead of static prior (ablation)PBO+AE · Munich rental datasetpairwise accuracy: 0.492 -> 0.569Improved
add autoencoder latent space with probabilistic prior on Munich datasetPBO · Munich rental datasetpairwise accuracy: 0.544 -> 0.569Improved
add autoencoder latent space with probabilistic prior with open-source LLMPBO · Idealista18 Madrid (gpt-oss-120b simulation)pairwise accuracy: 0.504 -> 0.573Improved
add LLM warm start to PBO+AE (ablation)PBO+AE · Idealista18 Madrid (LLM simulation)pairwise accuracyImproved

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