◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Will Cai

4 papers here

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author1
  • middle author2
  • last author1

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.CL2
  • cs.AI1
  • cs.CR1

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.AI2025

The Geometry of Harmfulness in LLMs through Subconcept Probing

McNair Shah, Saleena Angeline, Adhitya Rajendra Kumar +5

Recent advances in large language models (LLMs) have intensified the need to understand and reliably curb their harmful behaviours. We introduce a multidimensional framework for pr…

cs.CR2025

PromptArmor: Simple yet Effective Prompt Injection Defenses

Tianneng Shi, Kaijie Zhu, Zhun Wang +13

Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, c…

cs.CL2025

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs

Will Cai, Tianneng Shi, Xuandong Zhao +1

Commercial Large Language Model (LLM) APIs create a fundamental trust problem: users pay for specific models but have no guarantee that providers deliver them faithfully. Providers…

cs.CL2025

Improving LLM Safety Alignment with Dual-Objective Optimization

Xuandong Zhao, Will Cai, Tianneng Shi +4

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.