Papers by Yanlin Zhang
RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for large language models fail to capture complex interplay between functionality and security. |
| Approach: | They propose a benchmark for secure code generation constructed from real-world, high-risk Java repositories. |
| Outcome: | The proposed benchmarks highlight the gap between functional and secure code generation in LLMs. |
ArkRepoBench: A Repository-Level Code Completion Benchmark for HarmonyOS Development (2026.findings-acl)
Copied to clipboard
Yanlin Wang, Bowen Zhang, Yanli Wang, Daya Guo, Terry Yue Zhuo, Jiachi Chen, Mingwei Liu, Xingong Zhang, Zibin Zheng
| Challenge: | Despite the maturity of LLM-based code assistance for mainstream languages, the capabilities of ArkTS are largely unexplored. |
| Approach: | They propose to benchmark repository-level code completion for ArkTS using 7,519 samples from 20 official HarmonyOS repositories. |
| Outcome: | The proposed benchmark covers multiple difficulty levels and categorizes completion instances into Single-File, Cross-Filled Independent, and Cross-Filed Dependent settings based on dependency analysis. |
LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Cross-modal retrieval is essential for interpreting cultural heritage data, but its effectiveness is limited by incomplete or inconsistent textual descriptions. |
| Approach: | They propose a data augmentation framework that enhances cross-modal retrieval performance by improving the completeness and consistency of LLM-generated descriptions. |
| Outcome: | The proposed framework improves cross-modal retrieval performance by improving completeness and consistency of LLM-generated descriptions. |
Visually-Guided Policy Optimization for Multimodal Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing RLVRs lack visual faithfulness due to text-dominated reasoning . a novel framework to reinforce visual focus during policy optimization is proposed . |
| Approach: | They propose a framework to reinforce visual focus during policy optimization using visual attention compensation mechanism. |
| Outcome: | The proposed framework exhibits better visual activation and superior performance in multimodal reasoning and visual-dependent tasks. |
From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA (2026.findings-acl)
Copied to clipboard
Jing Zhang, Lianghong Guo, Yanlin Wang, Terry Yue Zhuo, Yong Wang, Mingwei Liu, Jiachi Chen, Ensheng Shi, Yuchi Ma, Hongyu Zhang, Zibin Zheng
| Challenge: | Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries. |
| Approach: | They conduct preliminary analysis of real user–LLM dialogues from WildChat to investigate the importance of Dev Knowledge QA in AI-assisted software development scenarios. |
| Outcome: | The proposed benchmark is based on real user–LLM dialogues from WildChat. |
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)
Copied to clipboard
Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang
| Challenge: | Current outcome-centric verification paradigms neglect potential errors in the derivation process. |
| Approach: | They propose a process-aware RLVR training paradigm utilizing verifiers selected via **PRIME**. |
| Outcome: | The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models. |
RACE: Retrieval-augmented Commit Message Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to automatically generate commit messages are repetitive or redundant. |
| Approach: | They propose a retrieval-augmented neural commit message generation method which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message. |
| Outcome: | The proposed method outperforms baselines on a large dataset with five programming languages and can boost existing Seq2Seq models in commit message generation. |
Exploring Representation-level Augmentation for Code Search (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent data augmentations for code search are at the raw-data level, which requires additional code analysis and training cost. |
| Approach: | They propose a general format of representation-level augmentation that unifies existing methods. |
| Outcome: | The proposed methods can boost the performance of code search models on a large-scale dataset. |
CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for code summarization do not capture rich information in ASTs . existing methods are labor-intensive and time-consuming to document code with good summaries manually. |
| Approach: | They propose a model that hierarchically splits and reconstructs ASTs by a neural network . they propose to use AST embeddings and a vanilla code token encoder to generate the model . |
| Outcome: | The proposed model splits and reconstructs ASTs into subtrees and then aggregates embeddings of subtreas to get the complete AST. |
Tackling Long Code Search with Splitting, Encoding, and Aggregating (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing pretraining models take the first 256 tokens of code snippets by default, limiting the input length to 512. |
| Approach: | They propose a baseline SEA model which splits long code into code blocks and aggregates them to obtain a comprehensive long code representation. |
| Outcome: | The proposed model can model long code without changing their internal structure and re-pretraining. |
Accelerating Code Search with Deep Hashing and Code Classification (2022.acl-long)
Copied to clipboard
| Challenge: | Code search is to search reusable code snippets from source code corpus based on natural languages queries. |
| Approach: | They propose a method to accelerate code search with deep hashing and code classification by using deep hashes and code hash. |
| Outcome: | The proposed method can save 90% of retrieval time while preserving at least 99% of retrievals accuracy. |
PhageBench: Can LLMs Understand Raw Bacteriophage Genomes? (2026.findings-acl)
Copied to clipboard
| Challenge: | phage genome annotation is a critical component of microbial ecosystems and antibiotics. |
| Approach: | They propose a benchmark to evaluate phage genome understanding by mirroring workflow of bioinformatics experts. |
| Outcome: | The benchmark outperforms baseline models in phage contig identification and host prediction. |
GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on specialized DNA models trained for sequence prediction or evaluate biological knowledge using text-only questions. |
| Approach: | They propose a benchmark to evaluate general-purpose LLMs on sequence-based genome inference tasks. |
| Outcome: | The proposed benchmark outperforms baseline models on sequence-based genome inference tasks. |
Dunhuang-Bench: How Well Do MLLMs Understand Cultural Heritage? (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models (MLLMs) have led to extensive evaluations on Chinese cultural benchmarks. |
| Approach: | They construct a large-scale benchmark comprising 486 images and 22,970 QA pairs to evaluate MLLMs' cultural understanding. |
| Outcome: | The proposed benchmark incorporates three task formats to evaluate MLLMs’ cultural understanding: Question Answering with Text Description, Multi-turn Dialogue, and Question Answers with Choices. |
From Logical to Computational Sparsity: Structure-Aware Block-Sparse Attention for Long-Code Completion (2026.acl-long)
Copied to clipboard
| Challenge: | Existing sparse attention methods for long-context generation pose high latency . general sparsity methods cause excessive accuracy degradation without considering code structure . |
| Approach: | They propose a training-free **S**tructure-**a**ware **b**lock-spa**r**s**e** attention mechanism that bridges the gap between logical and computational sparsity. |
| Outcome: | The proposed method reduces TTFT by 45-55% while maintaining accuracy within 3% of dense attention. |