AI Paper Atlas

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

ExpGuard: LLM Content Moderation in Specialized Domains

Minseok Choi, Dongjin Kim, Seungbin Yang, Subin Kim, Youngjun Kwak, Juyoung Oh, Jaegul Choo, Jungmin Son

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Safety alignment of LLMs · 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
add domain-specific data to the training set (ablation)ExpGuard · ExpGuardTest Totalprompt F1 (%): 85.3 -> 93.3Improved
add in-the-wild data to the training set (ablation)ExpGuard · ExpGuardTest Totalprompt F1 (%): 93.2 -> 93.3No clear effect
add in-the-wild data to the training set (ablation)ExpGuard · Public benchmarks (prompt, average)prompt F1 (%): 84.1 -> 85.7Improved
add human-written data to the training set (ablation)ExpGuard · Public benchmarks (response, average)response F1 (%): 73.9 -> 78.5Improved
train ExpGuard with domain-specific data versus WildGuardExpGuard vs WildGuard · ExpGuardTest Totalprompt F1 (%): 84.4 -> 93.3Improved
train ExpGuard versus WildGuardExpGuard vs WildGuard · ExpGuardTest Totalresponse F1 (%): 77.4 -> 92.7Improved
ExpGuard versus WildGuard on public benchmarksExpGuard · Public benchmarks (prompt, average)prompt F1 (%): 84.2 -> 85.7Improved
ExpGuard versus WildGuard on public benchmark responsesExpGuard · Public benchmarks (response, average)response F1 (%): 78.8 -> 78.5No clear effect
add 270 domain-specific jailbreak prompts to training (ExpGuard+) (ablation)ExpGuard · Domain-specific jailbreaksdetection rateImproved

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