Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation
cs.CL
Submitted: 2026-10-04
Updated: 2026-10-04
Terminology
Sources
- Program Synthesis with Large Language Models
- Demonstrating specification gaming in reasoning models
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents
- Scaling Agentic Verifier for Competitive Coding
- DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code Generation
- Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
- Code Llama: Open Foundation Models for Code
- CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- The Limits of Inference Scaling Through Resampling
- Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
- DecoPrompt : Decoding Prompts Reduces Hallucinations when Large Language Models Meet False Premises
- CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering