Sheng Guan — accepted AI-conference papers

2026

Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy Verifier

Yegor Denisov-Blanch, Joshua Kazdan, Jessica Chudnovsky, Rylan Schaeffer, Sheng Guan, Soji Adeshina +1

ICML 2026poster

Pass@$k$ and other methods of scaling inference compute can improve language model performance in domains with external verifiers, including mathematics and code, where incorrect candidates can be filtered reliably. This raises a natural question: can we similarly scale compute to elicit gains in tr…

Cited by 0 Source ↗Scholar ↗

2025

A Systematic Survey of Automatic Prompt Optimization Techniques

Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen +15

EMNLP 2025

Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. However, prompt engineering remains an impediment for end users due to rapid advances in models, tasks, and associated bes

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models

Sangmin Woo, Kang Zhou, Yun Zhou, Shuai Wang, Sheng Guan, Haibo Ding +1

NAACL 2025short

Large Vision Language Models (LVLMs) often suffer from object hallucination, which undermines their reliability. Surprisingly, we find that simple object-based visual prompting—overlaying visual cues (e.g., bounding box, circle) on images—can significantly mitigate such hallucination; however, diffe…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

Aiwei Liu, Sheng Guan, Yiming Liu, Leyi Pan, Yifei Zhang, Liancheng Fang +3

ICLR 2025spotlight

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing. However, current researches lack investigati…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

RoboGNN: Robustifying Node Classification under Link Perturbation

Sheng Guan, Hanchao Ma, Yinghui Wu

IJCAI 2022poster

Graph neural networks (GNNs) have emerged as powerful approaches for graph representation learning and node classification. Nevertheless, they can be vulnerable (sensitive) to link perturbations due to structural noise or adversarial attacks. This paper introduces RoboGNN, a novel framework that sim…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗