影响力指数

58.84/100

前 5.1%

全站排名 #3,269

发表论文13 篇

平均评分5.1

年均产出4.3 篇/年

Preslav Nakov

Full Professor@Mohamed bin Zayed University of Artificial Intelligence·阿联酋·OpenReview

研究方向

Large Language Models · Fake News · fact-checking · disinformation · misinformation · propaganda · media bias · Question Answering · Machine Translation

6.0

DP-Fusion: Token-Level Differentially Private Inference for Large Language Models

ICLR 2026Poster

二作

5.5

Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

ICLR 2026Rejected

5.3

A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA

ICLR 2026Poster

4.8

Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search

ICLR 2026Poster

4.0

ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability

ICLR 2026Withdrawn

3.5

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory, and Test Time Compute Scaling

ICLR 2026Withdrawn

3.5

From Guanyin, UFOs to Paradise: Capturing Cultural Variation in Dream Interpretation

ICLR 2026Withdrawn

通讯

3.0

Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control

ICLR 2026Withdrawn

二作

2.5

YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation

ICLR 2026Withdrawn

7.3

CoCoA: A Minimum Bayes Risk Framework Bridging Confidence and Consistency for Uncertainty Quantification in LLMs

NeurIPS 2025Poster

7.3

MuSLR: Multimodal Symbolic Logical Reasoning

NeurIPS 2025Poster

6.3

Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting

合作者 (20)