CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation

cs.SE, cs.AI

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 15 pages. Code: https://github.com/fangz-cs/Contra

Code: https://github.com/fangz-cs/Contra

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
• ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation
• Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation
• CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models
• Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks
• Can Code Language Models Learn Clarification-Seeking Behaviors?

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties