Nouha Dziri
~Nouha_Dziri2
13
论文总数
6.5
年均投稿
平均评分
接收情况12/13
会议分布
ICLR
7
COLM
3
NeurIPS
2
ICML
1
发表论文 (13 篇)
20258 篇
4
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
ICML 2025Poster
3
SafetyAnalyst: Interpretable, transparent, and steerable LLM safety moderation
ICLR 2025Rejected
3
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
ICLR 2025Spotlight
4
Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations
NeurIPS 2025Poster
4
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
ICLR 2025Poster
3
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
COLM 2025Poster
4
AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
ICLR 2025Oral
4
2 OLMo 2 Furious (COLM’s Version)
COLM 2025Poster
20245 篇
4
CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting
COLM 2024Poster
4
The Generative AI Paradox: “What It Can Create, It May Not Understand”
ICLR 2024Poster
4
The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
ICLR 2024Poster
4
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
ICLR 2024Oral
4
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
NeurIPS 2024Poster