Papers by Ma Bowen

16 papers
Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) driven by In-Context Learning (ICL) have improved performance of text-to-SQL.
Approach: They propose a strategy to mitigate hallucinations in large language models driven by In-Context Learning (ICL) they propose TA-SQL, a text-to-Sql framework that encourages LLMs to take advantage of similar tasks rather than starting from scratch.
Outcome: The proposed framework improves the performance of the GPT-4 model by 21.23% on BIRD dev.
ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)

Copied to clipboard

Challenge: Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth.
Approach: They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning.
Outcome: The proposed framework outperforms existing methods on ICLR 2025 papers.
I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing (2026.acl-long)

Copied to clipboard

Challenge: Existing text-guided image editing methods rely on end-to-end pixel-level inpainting paradigm . existing models lack such intermediate representations and Reasoning-then-action process .
Approach: They propose a "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment.
Outcome: The proposed paradigm outperforms existing methods in compositional editing tasks.
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Copied to clipboard

Challenge: Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach: They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome: Texar supports machine translation, summarization, dialog, content manipulation, and more.
QSpell 250K: A Large-Scale, Practical Dataset for Chinese Search Query Spell Correction (2025.naacl-industry)

Copied to clipboard

Challenge: Chinese Search Query Spell Correction is a task designed to identify and correct typographical errors within queries.
Approach: They propose a large-scale benchmark specifically developed for Chinese Query Spell Correction.
Outcome: The proposed benchmark covers a broad range of topics, including formal entities, everyday colloquialisms and idiomatic expressions.
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)

Copied to clipboard

Challenge: Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting.
Approach: They propose a representation-aware model merging framework for continual learning without access to historical data.
Outcome: The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios.
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach: They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome: The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.
Best Practices for Distilling Large Language Models into BERT for Web Search Ranking (2025.coling-industry)

Copied to clipboard

Challenge: Recent studies have highlighted the potential of Large Language Models (LLMs) as zero-shot relevance rankers.
Approach: They propose to use a ranking loss to transfer ranking knowledge from LLMs to smaller models like BERT.
Outcome: The proposed model has been successfully integrated into a commercial web search engine as of February 2024.
LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks for long-form generation assess real-world queries with hard-to-verify metrics or use synthetic setups that overlook real-life intricacies.
Approach: They propose a new approach that balances verifiable and real-world assessment with Target-Anchored Evaluation.
Outcome: The proposed model balances real-world and verifiable assessment with Target-Anchored Evaluation (TAE) it generates queries, textual materials, and anchors based on verifier targets within real-life scenarios .
A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution (2024.naacl-long)

Copied to clipboard

Challenge: Existing state-of-the-art event coreference resolution systems rely on spurious and spurious associations in the input mention pair text.
Approach: They propose a rationale-centric counterfactual data augmentation method that leverages the debiasing capability of counterfact data haussed by LLM-in-the-loop to mitigate spurious association while emphasizing causation.
Outcome: The proposed method achieves state-of-the-art on three popular cross-document benchmarks and demonstrates robustness in out-of domain scenarios.
SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to self-correct text-to-SQL fail to demonstrate underlying reasoning path . authors propose **SHARE**, a self-revolution assistant for text-based error correction .
Approach: They propose a "SHARE" assistant that enables LLMs to perform more precise error localization and efficient correction.
Outcome: The proposed assistant performs more precise error localization and efficient correction for monolithic SQL queries.
R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive capabilities in multi-step and long-chain reasoning, but extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge.
Approach: They propose a framework for Reasoning–Search integration that integrates multi-reward signals to optimize the reasoning–search interaction trajectories.
Outcome: Experiments on seven datasets show that R-Search significantly outperforms mainstream RAG baselines.
Graph-to-Text Generation with Dynamic Structure Pruning (2022.coling-1)

Copied to clipboard

Challenge: Recent studies show that explicitly modeling the input graph structure can significantly improve the performance.
Approach: They propose a structure-aware cross-attention mechanism to re-encode the graph representation conditioning on the newly generated context at each decoding step.
Outcome: The proposed model improves performance on two graph-to-text datasets with only minor increase on computational cost.
Label Words as Local Task Vectors in In-Context Learning (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being in-context learning (ICL).
Approach: They hypothesized that the network creates a task vector in specific positions during ICL, which can be computed by averaging across the dataset.
Outcome: The proposed model can achieve zero-shot performance with dummy inputs comparable to few-shot learning by patching the global task vector.
Micro-Act: Mitigate Knowledge Conflict in Question Answering via Actionable Self-Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to mitigate knowledge conflict by comparing two knowledge sources can overwhelm LLMs with extraneous or lengthy contexts.
Approach: They propose a framework that decomposes knowledge into fine-grained comparisons . they propose 'Micro-Act' framework that allows for reasoning beyond the superficial context .
Outcome: The proposed framework achieves significant increase in QA accuracy over state-of-the-art baselines on five benchmark datasets.

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