CORTEXA
← Browse
arxivcs.AIcs.CL2026-06-30

CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes

Yuchen Huang, Xiang Li, Zhenqing Ling, Sijia Li, Qianli Shen, Daoyuan Chen, Yi R. Fung, Yaliang Li

Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While existing benchmarks either isolate text editing or entangle it with code and tool execution, it remains unclear whether LLMs can directly and faithfully execute these compositional, order-sensitive data refinement recipes. To fill this gap, we introduce CDR-Bench, a comprehensive benchmark featuring 3,462 high-quality tasks spanning four real-world data refinement domains and 29 distinct operators. Our benchmark evaluates models across atomic, order-agnostic, and order-sensitive settings, leveraging deterministic reference outputs to enable exact evaluation. Experiments on 10+ state-of-the-art LLMs reveal consistent failure patterns: performance degrades sharply in compositional settings, and order-sensitive recipe success collapses. These findings underline that current LLMs lack the procedural faithfulness required for reliable compositional data refinement.

View free PDFSource page

Related papers

arxivcs.AIcs.CLcs.LO2026-06-30

Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization

Ke Zhang, Patricio Gallardo Candela, Sudhir Murthy, Yi Xie, Zhi Wang, Maziar Raissi

Theorem-proving benchmarks evaluate proof search against fixed formal statements, but natural-language-to-Lean formalization must generate the formal statement itself. In this setting, compilation is only a validity check: a Lean declaration may type-check while omitting hypothes…

View free PDFSource page
arxivcs.SEcs.AIcs.CL2026-07-02

TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution

Jiale Amber Wang, Kaiyuan Wang, Pengyu Nie

Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing test generation and update benchmarks often isolate the test from the code change, and rely on static metadata that does not verif…

View free PDFSource page
arxivcs.CLcs.AI2026-07-10

Faithful by Design: Evaluating and Improving LLM-Generated Clinical Trial Summaries for Multi-Stakeholder Audiences

Robert Williams

Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context. This study introduces a benchmark evaluation framework for measur…

View free PDFSource page
arxivcs.CLcs.AI2026-07-09

UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing

Xinlong Zhao, Dongsheng Liu, Hengyu Zhao, Zixuan Fu, Zheng Wang, Jie Cai, et al.

As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale co…

View free PDFSource page
arxivcs.AIcs.CLcs.LG2026-07-19

Otap:Structure-Aware Optimal Transport for Evaluating Planning and Execution in Agent Trajectories

Babak Barazandeh, Subhabrata Majumdar, George Michailidis

Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current evaluation metrics reduce such a trajectory to a binary success flag or compare it against a reference by exact matching. A success flag cann…

View free PDFSource page