AI Paper Atlas

Research map / Large language models / Agents, code and math

EMODIS: A Benchmark for Context-Dependent Emoji Disambiguation in Large Language Models

Jiacheng Huang, Ning Yu, Xiaoyin Yi

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 1 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 API-based GPT-4 instead of open-source modelsEMODIS emoji disambiguation · EMODIS overallpair-wise accuracy (Accp, %): 58.8 (GPT-4) vs 34.7 (Qwen-14B)Improved
scale LLaMA from 7B to 13BLLaMA · EMODIS overallpair-wise accuracy (Accp, %): 13.5 -> 21.3Improved
scale Qwen from 7B to 14BQwen · EMODIS overallpair-wise accuracy (Accp, %): 26.5 -> 34.7Improved
use social intent contexts instead of temporal contextsGPT-4 · EMODISpair-wise accuracy (Accp, %): 64.5 -> 54.2Hurt
use open-source models (LLaMA-7B) instead of GPT-4 on context awarenesscontext sensitivity · EMODISScore_ca: 0.406 -> 0.254Hurt
replace human with best LLM on context awarenesscontext sensitivity · EMODISScore_ca: 0.959 -> 0.406Hurt
swap GPT-4 judge for human judge (ablation)EMODIS evaluation · EMODISAccp (%): 59.6 (GPT-4 judge) vs 60.1 (human judge) for GPT-4 outputsNo 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