Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
JUDGERAIL:HARNESSINGOPEN-SOURCELLMSFOR FASTHARMFUL TEXTDETECTIONWITH JUDICIAL PROMPTINGANDLOGITRECTIFICATION
Published in ICLR 2025(Reject), 2024
Largelanguagemodels(LLMs)simultaneouslyfacilitatethegenerationandde tectionofharmful text. LeadingLLMdevelopers, suchasOpenAI,Meta, and Google, aredrivingaparadigmshift in thedetectionofharmful text,moving fromconventionaldetectorstofine-tunedLLMs.However, thesenewlyreleased models,whichrequiresubstantialcomputationalanddataresources,havenotyet beenthoroughlyinvestigatedfortheireffectivenessinthisnewparadigm. Inthis work,weproposeJudgeRail, anovelandgenericframeworkthatguidesopen sourceLLMstoadheretojudicialprinciplesduringtextmoderation.Additionally, weintroduceanewlogit rectificationmethodthatcanextractanLLM’sclassi ficationintent, effectivelycontrols itsoutput format, andacceleratesdetection. Byintegratingseveral top-performingopen-sourceLLMs intoJudgeRailwith out anyfine-tuningandevaluatingthemagainstOpenAIModerationAPI,Lla maGuard3, ShieldGemma, andother conventionalmoderationsolutionsacross variousdatasets,includingthosespecificallydesignedforjailbreakingLLMs,we demonstrate that JudgeRail canadapt theseLLMs tobecompetitivewithfine tunedmoderationmodels andsignificantlyoutperformconventional solutions. Moreover,weevaluateallmodelsfordetectionlatency, acriticalyet rarelyex aminedpracticalaspect,andshowthatLLMswithJudgeRailrequireonly46%to 55%ofthetimeneededbyLlamaGuard3andShieldGemma.Thegenericnature andcompetitiveperformanceofJudgeRailhighlight itspotential forpromoting thepracticalityofLLM-basedharmful textdetectors.Warning: sometextex amplespresentedinthispapermaybeoffensivetosomereaders.
Paper Title Number 4
Published in Course assignment, 2025
This article is an assignment for the course “History of Computer Science Thought 2025” at Zhejiang University
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.