◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Mengdi Wang

9 papers hereh-index 11568 citations22 works total

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

author position
  • middle author6
  • last author2

Across the 8 of 9 papers where every author was matched, so the position is known.

fields
  • cs.CL4
  • cs.AI2
  • cs.LG2
  • cs.CR1
same name
  • Mengdi Wang — 26 papers, h 13
  • Mengdi Wang — 23 papers, h 11
  • Mengdi Wang — 14 papers, h 8
  • Mengdi Wang — 9 papers, h 11
  • Mengdi Wang — 8 papers, h 4
  • Mengdi Wang — 7 papers, h 6

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators
Showing cs.CLShow all

4 papers · 1 filter

cs.CL2025

LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds

James Beetham, Souradip Chakraborty, Mengdi Wang +3

Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or tr…

cs.CL2025

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment

Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag +7

Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effect…

cs.CL2024

MaxMin-RLHF: Alignment with Diverse Human Preferences

Souradip Chakraborty, Jiahao Qiu, Hui Yuan +5

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an ap…

cs.CL2024

Transfer Q Star: Principled Decoding for LLM Alignment

Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin +4

Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billi…

◍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.