3 papers
cs.LG2026
Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation
Mahdi Erfanian, Nelson Daniel Troncoso, Aashna Garg +4
Small open-source code models that power IDE autocomplete still emit hallucinated Fill-in-the-Middle (FIM) completions: syntactically natural calls to methods, parameters, variable…
cs.CV2026
PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors
Himangi Mittal, Gaurav Mittal, Nelson Daniel Troncoso +1
Computer Use Agents (CUAs) fundamentally rely on graphical user interface (GUI) grounding to translate language instructions into executable screen actions, but editing-level groun…
cs.LG2026
Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks
Mahdi Erfanian, Nelson Daniel Troncoso, Aashna Garg +4
Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions such as invented API methods, i…