相关论文: Code-QA-Bench: Separating Code Reasoning from Docu…

Code summarization is a critical task in natural language processing and software engineering, which aims to generate concise descriptions of source code. Recent advancements have improved the quality of these summaries, enhancing code…

PDE-to-solver code generation aims to automatically synthesize executable numerical solvers from partial differential equation (PDE) specifications. This task requires not only understanding the mathematical structure of PDEs, but also…

The increasing demand for domain-specific evaluation of large language models (LLMs) has led to the development of numerous benchmarks. These efforts often adhere to the principle of data scaling, relying on large corpora or extensive…

Legal question answering (QA) has attracted increasing attention from people seeking legal advice, which aims to retrieve the most applicable answers from a large-scale database of question-answer pairs. Previous methods mainly use a…

Automated code review (CR) is a key application for Large Language Models (LLMs), but progress is hampered by a "reality gap": existing benchmarks evaluate models on isolated sub-tasks using simplified, context-poor data. This fails to…

Due to the concise and structured nature of tables, the knowledge contained therein may be incomplete or missing, posing a significant challenge for table question answering (TableQA) and data analysis systems. Most existing datasets either…

Formal verification is the next frontier for ensuring the correctness of code generated by Large Language Models (LLMs). While methods that co-generate code and formal specifications in formal languages, like Dafny, can, in principle, prove…

Retrieving real-time information is a fundamental capability for search-integrated agents in real-world applications. However, existing benchmarks are predominantly static and therefore fail to capture the temporal dynamics of information…

Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing…

While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the degradation of High-Density Reasoning where Chain-of-Thought…

Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have…

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual…

Code review is a fundamental process in software development that plays a pivotal role in ensuring code quality and reducing the likelihood of errors and bugs. However, code review can be complex, subjective, and time-consuming. Quality…

We introduce an expert curated, real-world benchmark for evaluating document-grounded question-answering (QA) motivated by generic drug assessment, using the U.S. Food and Drug Administration (FDA) drug label documents. Drug labels contain…

The Codex model has demonstrated extraordinary competence in synthesizing code from natural language problem descriptions. However, in order to reveal unknown failure modes and hidden biases, such large-scale models must be systematically…

Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and…

Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…

Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this setting is still poorly…

While LLM-Based agents, which use external tools to solve complex problems, have made significant progress, benchmarking their ability is challenging, thereby hindering a clear understanding of their limitations. In this paper, we propose…

Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One…