AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization

Yuzhuo Bai, Shitong Duan, Muhua Huang, Jing Yao, Zhenghao Liu, Peng Zhang, Tun Lu, Xiaoyuan Yi, Maosong Sun, Xing Xie

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems · 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
apply IROTE self-reflectionQwen2.5-7B-Instruct · Table 2 averageavg score: 60.49 -> 80.01Improved
apply IROTE self-reflectionMistral-7B-Instruct-v0.3 · Table 2 averageavg score: 60.91 -> 78.65Improved
apply IROTE self-reflectionGPT-4o · Table 2 averageavg score: 57.33 -> 78.20Improved
apply IROTE self-reflectionQwen2.5-7B-Instruct · MoralPrompt (lower better)violation score: 72.25 -> 36.07Improved
IROTE vs EvoPromptGPT-4o · Table 2 averageavg score: 77.15 vs 78.20No clear effect
IROTE vs Anthology on Offensive/RacistGPT-4o · Offensivescore: 3.36 vs 3.38 (Racist 2.58 vs 2.76)Hurt
IROTE vs AnthologyGPT-4o · AdAEMscore: 93.06 vs 92.70Mixed
use Similarity example selectionMistral-7B-Instruct-v0.3 · Table 2 averageavg score: 60.91 -> 54.51Hurt
use ICDPO in-context selectionQwen2.5-7B-Instruct · Table 2 averageavg score: 60.49 -> 67.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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