Xiangyuan Guan

Xianfu Cheng, Wei Zhang, Shiwei Zhang et al. · bytedance

The increasing application of multi-modal large language models (MLLMs) across various sectors have spotlighted the essence of their output reliability and accuracy, particularly their ability to produce content grounded in factual information (e.g. common and domain-specific knowledge). In this work, we introduce SimpleVQA, the first comprehensive multi-modal benchmark to evaluate the factuality ability of MLLMs to answer natural language short questions. SimpleVQA is characterized by six key features: it covers multiple tasks and multiple scenarios, ensures high quality and challenging queries, maintains static and timeless reference answers, and is straightforward to evaluate. Our approach involves categorizing visual question-answering items into 9 different tasks around objective events or common knowledge and situating these within 9 topics. Rigorous quality control processes are implemented to guarantee high-quality, concise, and clear answers, facilitating evaluation with minimal variance via an LLM-as-a-judge scoring system. Using SimpleVQA, we perform a comprehensive assessment of leading 18 MLLMs and 8 text-only LLMs, delving into their image comprehension and text generation abilities by identifying and analyzing error cases.

Wei Zhang, Xianfu Cheng, Yi Zhang et al.

Log parsing, a vital task for interpreting the vast and complex data produced within software architectures faces significant challenges in the transition from academic benchmarks to the industrial domain. Existing log parsers, while highly effective on standardized public datasets, struggle to maintain performance and efficiency when confronted with the sheer scale and diversity of real-world industrial logs. These challenges are two-fold: 1) massive log templates: The performance and efficiency of most existing parsers will be significantly reduced when logs of growing quantities and different lengths; 2) Complex and changeable semantics: Traditional template-matching algorithms cannot accurately match the log templates of complicated industrial logs because they cannot utilize cross-language logs with similar semantics. To address these issues, we propose ECLIPSE, Enhanced Cross-Lingual Industrial log Parsing with Semantic Entropy-LCS, since cross-language logs can robustly parse industrial logs. On the one hand, it integrates two efficient data-driven template-matching algorithms and Faiss indexing. On the other hand, driven by the powerful semantic understanding ability of the Large Language Model (LLM), the semantics of log keywords were accurately extracted, and the retrieval space was effectively reduced. Notably, we launch a Chinese and English cross-platform industrial log parsing benchmark ECLIPSE- BENCH to evaluate the performance of mainstream parsers in industrial scenarios. Our experimental results across public benchmarks and ECLIPSE- BENCH underscore the superior performance and robustness of our proposed ECLIPSE. Notably, ECLIPSE both delivers state-of-the-art performance when compared to strong baselines and preserves a significant edge in processing efficiency.

Jian Yang, Xianglong Liu, Weifeng Lv et al.

Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot (Microsoft), Cursor (Anysphere), Trae (ByteDance), and Claude Code (Anthropic). While the field has evolved dramatically from rule-based systems to Transformer-based architectures, achieving performance improvements from single-digit to over 95\% success rates on benchmarks like HumanEval. In this work, we provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs, systematically examining the complete model life cycle from data curation to post-training through advanced prompting paradigms, code pre-training, supervised fine-tuning, reinforcement learning, and autonomous coding agents. We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder), critically examining the techniques, design decisions, and trade-offs. Further, we articulate the research-practice gap between academic research (e.g., benchmarks and tasks) and real-world deployment (e.g., software-related code tasks), including code correctness, security, contextual awareness of large codebases, and integration with development workflows, and map promising research directions to practical needs. Last, we conduct a series of experiments to provide a comprehensive analysis of code pre-training, supervised fine-tuning, and reinforcement learning, covering scaling law, framework selection, hyperparameter sensitivity, model architectures, and dataset comparisons.