cs.CLMay 26, 2026

ContextGuard: Structured Self-Auditing for Context Learning in Language Models

Authors: Hongbo JinChi WangHaoran TangZhongjing DuXu JiangJingqi TianQiaoman ZhangJiayu Ding

Organizations: Peking University · SCUT · Tsinghua University

Abstract

Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextual knowledge. These failures are often not wholesale reasoning collapses: in context-rich tasks, models may follow the central reasoning path while missing peripheral, persistent, or format-sensitive requirements.

Explore similar work

CardsList