Guotong Geng

8 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) ⭐ Rising Star (8) ⚡ Prolific Year · Productive

Venues

ACL (4) AAAI (3) EMNLP (1)

Top co-authors

Zhunchen Luo (7) Minghao Hu (6) Jun Zhang (5) Cong Gao (4) Bo Zhang (4) Bingxu Han (3) Linkang Yang (3) Wen Yao (3) Xiaoying Bai (3) Zhong Wang (3)

Research topics

Artificial Intelligence (8) Core AI (8) Machine Learning (4) Natural Language Processing (2) Generation (2) Optimization & Theory (2) Deep Learning (1) Application Areas (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1)

Keywords

large language model (4) confidence calibration (2) long-form generation (2) mathematical reasoning (2) model safety (1) harmful content (1) prompt generation (1) jailbreak attack (1) decoding strategy (1) hallucination detection (1) multi-agent collaboration (1) expected calibration error (1) structured data (1) predictive distribution (1) confidence estimation (1) knowledge retrieval (1) reasoning chain (1) process reward model (1) large reasoning model (1) adversarial fine-tuning (1)

Papers

DeepWriter: A Multi-Agent Collaboration Framework for Information-rich Ultra-long Book Writing AAAI 2026 DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs ACL 2026 Global-Local Confidence Fusion for Hallucination Detection in Mathematical Reasoning Task AAAI 2026 IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking ACL 2026 SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking ACL 2026 WikiMAG: A Multi-Agent Guided Framework for Generating Structured Wikipedia-like Articles AAAI 2026 Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model ACL 2025 SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models EMNLP 2025