AI Paper Atlas

Research map / Large language models / Alignment and preferences

Robust Multi-Objective Controlled Decoding of Large Language Models

Seongho Son, William Bankes, Sangwoong Yoon, Shyam Sundhar Ramesh, Xiaohang Tang, Ilija Bogunovic

ICLR 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 9 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
use RMOD (maximin worst-case weights) instead of uniform-weight controlled decodinggemma-2-2b-it · HH (gpt-4o judge)worst-case win rate (%): 57.6% -> 59.1%Improved
distill RMOD outputs into the policy via SFTgemma-2-2b-it · HH (gpt-4o judge)worst-case win rate (%): 57.9% vs CD-Uniform 57.6%Improved
increase lambda (ablation)RMOD · HHweight sparsity / worst-case focusImproved
increase block size B above 16 (ablation)RMOD · HHworst-case win rateHurt
increase number of objectives up to 10 (ablation)RMOD · ValuePrismworst-case rewardHurt
increase K to 16 in best-of-K on harmlessness reward directly (ablation)BoK-Harmless · HH (gpt-4o judge)worst-case win rate (%): 52.3% -> 51.1% (K=2 to K=16)Hurt
use worst-case weights computationRMOD · HHlatency: less than 4.5% higher latencyNo 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