paper-with-me

Papers

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

2026-05-26 · Hongbo Jin, Chi Wang, Haoran Tang, Zhongjing Du, Xu Jiang, Jingqi Tian, Qiaoman Zhang, Jiayu Ding arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.26827

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs

2026-05-12 · Chaeyoung Jung, Kyeongha Rho, Joon Son Chung arxiv

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing O…

ContextGuard-LVLM: Enhancing News Veracity through Fine-grained Cross-modal Contextual Consistency Verification

2025-08-08 · Sihan Ma, Qiming Wu, Ruotong Jiang, Frank Burns arxiv

The proliferation of digital news media necessitates robust methods for verifying content veracity, particularly regarding the consistency between visual and textual information. Traditional approaches often fall short i…

Logical Reasoning

Adaptive Plan-Execute Framework for Smart Contract Security Auditing

2025-05-21 · Zhiyuan Wei, Jing Sun, Zijian Zhang, Zhe Hou 외

Large Language Models (LLMs) have shown great promise in code analysis and auditing; however, they still struggle with hallucinations and limited context-aware reasoning. We introduce SmartAuditFlow, a novel Plan-Execute…

RAGRetrieval-augmented GenerationVulnerability Detection

A Practice Auditing Framework for Large Language Model Use: Collective Empiricism, Pseudo-Rational Cognition, and Governance of AI-Generated Content

2026-06-02 · Yang Zhao, Yingshuo Li, Zeyu Zhang arxiv

Large language models are increasingly used for knowledge acquisition, code generation, academic writing, and agent-based automation. In these settings, users may obtain highly structured answers, plans, and judgments wi…

Code Generation

FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs

2025-10-10 · Yan Wang, Keyi Wang, Shanshan Yang, Jaisal Patel 외 arxiv

Going beyond simple text processing, financial auditing requires detecting semantic, structural, and numerical inconsistencies across large-scale disclosures. As financial reports are filed in XBRL, a structured XML form…

Information ExtractionMathematical Reasoning