AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

User-Aware Active Knowledge Acquisition for Emotional Support Dialogue

Mufan Xu, Kehai Chen, Jiahao Hu, Xinchao Xu, Muyun Yang, Tiejun Zhao, Min Zhang

ICML 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 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 knowledge acquisition and reuse (ablation)UKA · Sentient Eval (Qwen3-235B-A22B)average emotion score: 70.5 -> 82.9Improved
add ToM uncertainty (belief tracking) (ablation)UKA · Sentient Eval (Qwen3-235B-A22B)average emotion score: 79.2 -> 82.9Improved
add active candidate response selection (ablation)UKA · Sentient Eval (Qwen3-235B-A22B)average emotion score: 78.1 -> 82.9Improved
use ToM uncertainty instead of LM generation probability (ablation)UKA · Sentient Eval (Qwen3-235B-A22B)average emotion score: 82.5 -> 82.9No clear effect
use belief-aware retrieval instead of random knowledge (ablation)UKA · Sentient Eval (Qwen3-235B-A22B)average emotion score: 76.3 -> 82.9Improved
increase candidate set size N from 1 to 4 (ablation)UKA · Sentient Eval (Qwen3-235B-A22B)average emotion score: 78.1 -> 81.1Improved
increase hypothesis budget M from 1 to 3 at N=4 (ablation)UKA · Sentient Eval (Qwen3-235B-A22B)average emotion score: 80.9 -> 82.9Improved
increase candidate set size N from 1 to 4 (ablation)UKA · Sentient Eval (Qwen3-235B-A22B) AvoidantAvo. score: 93.1 -> 86.7Hurt
grow knowledge base from 0 to 200+ entries (ablation)UKA · Sentient Evalaverage emotion score: 70.5 -> 82.9Improved
add UKA on top of prompting baselineQwen3-32B · Sentient Evalaverage emotion score: 28.5 -> 33.9Improved
add MetaMind-style ToM promptingQwen3-32B · Sentient Evalaverage emotion score: 28.5 -> 21.3Hurt
use UKA instead of PRINCIPLESSeed-1.6-36B · ESConvsuccess rate: 0.450 -> 0.525Improved

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