AI Paper Atlas

Research map / Large language models / Alignment and preferences

Expectation Alignment of Language Models for Real-World User Expectations

Miaomiao Li, Yang Wang, Bin Liang, Shudong Liu, Zhiwei Zhang, Kam-Fai Wong

ICML 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 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 LENS latent expectation projectorLLaMA-3.1-8B · ExpectBench overallexpectation satisfaction: 2.17 -> 2.37Improved
add LENS latent expectation projectorMistral-7B · ExpectBench overallexpectation satisfaction: 2.39 -> 2.50Improved
supervised fine-tuning on gold expectations (SFT-Exp) instead of frozen model (ablation)LLaMA-3.1-8B · ExpectBench overallexpectation satisfaction: 2.17 -> 2.21No clear effect
supervised fine-tuning on gold expectations (SFT-Exp) (ablation)Mistral-7B · ExpectBench overallexpectation satisfaction: 2.39 -> 2.39No clear effect
fine-tune on responses (SFT-Resp) (ablation)LLaMA-3.1-8B · ExpectBench overallexpectation satisfaction: 2.17 -> 2.33Improved
fine-tune on responses (SFT-Resp) (ablation)Mistral-7B · ExpectBench overallexpectation satisfaction: 2.39 -> 2.44Improved
use LENS instead of SFT-Resp (ablation)LLaMA-3.1-8B · ExpectBench overallexpectation satisfaction: 2.33 -> 2.37Improved
use LENS instead of SFT-Resp (ablation)Mistral-7B · ExpectBench overallexpectation satisfaction: 2.44 -> 2.50Improved
use LENS instead of SFT-Resp on Cx dimension (ablation)LLaMA-3.1-8B · ExpectBench dimension Cxexpectation satisfaction: 2.36 -> 2.41Improved
use LENS instead of SFT-Resp on Cr dimension (ablation)LLaMA-3.1-8B · ExpectBench dimension Crexpectation satisfaction: 2.29 -> 2.29No clear effect
increase prediction budget k up to 10six LLMs · Expectation prediction coveragecoverageImproved

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