6 papers
Gap Detection: Mitigating Homogenization through Demand and Defensibility
Xucheng Yu, Haibo Jin, Xiaoqi Wang +2
Language models often produce semantically similar answers to open-ended questions, even when many plausible alternatives exist. Generating useful alternatives requires identifying…
Large-scale Repository Engineering via Agent-Native Reusable Code Primitives
Haibo Jin, Peng Kuang, Xucheng Yu +3
Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete repositories remains difficult b…
Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
Haibo Jin, Suijin Wang, Xucheng Yu +2
Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, existing approaches suffer from two…
Understanding Content Moderation in Large Language Models through Restricted Books: From Refusal to Warning
Xucheng Yu, Emily Knox, Haohan Wang
As large language models enter everyday information pipelines, understanding how they handle sensitive topics matters as much as understanding whether they handle them at all. We s…
SCI-Defense: Detecting Persuasion-Structured Manipulation of LLM-Based Ranking in Generative Engines
Xucheng Yu, Haibo Jin, Huimin Zeng +1
Generative engine optimization (GEO) has reshaped how sellers compete for visibility in LLM-generated rankings. By embedding persuasive arguments in the content they control, selle…
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models
Han Wang, Yifan Sun, Brian Ko +8
Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer…