Papers by Weishi Wang

7 papers
Towards Low-Resource Automatic Program Repair with Meta-Learning and Pretrained Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in deep learning (DL) based APR models have demonstrated promising results by learning from large-scale bug-fix examples in a data-driven manner.
Approach: They propose a meta-learning framework integrated with code pretrained language models to generate fixes for low-resource bugs with limited training samples.
Outcome: The proposed framework learns better error-specific knowledge from high-resource bugs through efficient first-order meta-learning optimization, which allows for a faster adaptation to the target low-resourced bugs.
Rethinking Reading Order: Toward Generalizable Document Understanding with LLM-based Relation Modeling (2026.eacl-long)

Copied to clipboard

Challenge: Document understanding requires modeling structural and semantic relationships between layout elements within the document without human supervision.
Approach: They propose a cost-effective paradigm that leverages large language models to infer global RO and inter-element layout relations without human supervision.
Outcome: Experiments on Semantic Entity Recognition, Entity Linking, and Document Question Answering show that the proposed model improves on baseline models while preserving the robustness of existing models.
Retrieving Multimodal Information for Augmented Generation: A Survey (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly using multimodality to augment their generation ability, but there is no unified perception of at which stage and how to incorporate different modalities.
Approach: They propose to use multimodality to augment Large Language Models (LLMs) this will provide scholars with a deeper understanding of the methods' applications and encourage them to adapt existing techniques to the fast-growing field of LLMs.
Outcome: The proposed methods improve factuality, reasoning, interpretability, and robustness of the generated content.
CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces.
Approach: They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings.
Outcome: The citycube benchmark examines the performance of current vision-language models in urban environments.
XCodeEval: An Execution-based Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.
Approach: They propose to use a multilingual multitask benchmark to evaluate large language models that can generate codes from natural language descriptions, repair buggy codes, and translate between languages.
Outcome: The proposed model performs 7 tasks covering up to 11 languages with execution-level parallelism and 25 M document-level coding examples (16.5 B tokens)
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Pre-trained models for Natural Languages (NL) like BERT and GPT have been shown to transfer well to Programming Languages.
Approach: They propose a unified pre-trained encoder-decoder Transformer model that leverages the code semantics conveyed from the developer-assigned identifiers.
Outcome: The proposed model outperforms existing models on understanding and generation tasks and can capture semantic information from code.
Response Selection for Multi-Party Conversations with Dynamic Topic Tracking (2020.emnlp-main)

Copied to clipboard

Challenge: Existing response selection methods focus on a two-party single-conversation scenario.
Approach: They propose a multi-task learning framework that frames response selection as a dynamic topic tracking task to match the topic between the response and relevant conversation context.
Outcome: The proposed framework outperforms existing methods on an Ubuntu IRC dataset in response selection and topic disentanglement tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations