Papers by Xiangliang Zhang

32 papers
MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training (2026.acl-long)

Copied to clipboard

Challenge: Existing systems for multi-turn Text-to-SQL are limited to a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs.
Approach: They propose to train an agentic training framework for long-horizon multi-turn Text-to-SQL that uses a Markov Decision Process to generate a query per turn without execution, explicit verification, and refinement.
Outcome: Experiments on CoSQL and SParC show that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing.
ArMATH: a Dataset for Solving Arabic Math Word Problems (2022.lrec-1)

Copied to clipboard

Challenge: This paper is the first to use deep learning methods to solve Arabic MWPs . it is also the first study to use transfer learning to solve MWp across different languages .
Approach: They contribute to the first large-scale dataset for Arabic Math Word Problems . they use deep learning methods to solve Arabic MWPs and a transfer learning model to promote performance .
Outcome: The proposed model improves Arabic MWP solvers by 3% over the existing model.
Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation (2021.acl-long)

Copied to clipboard

Challenge: Existing related work generation models are inflexible and extract sentences from multiple papers to form a related work discussion.
Approach: They propose a Relation-aware Related work generator which generates an abstractive related work from the given multiple scientific papers in the same research area.
Outcome: The proposed model improves over existing models and can be used to familiarize researchers with the state of the art in the field.
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been recognized for their impressive capabilities in natural language processing (NLP).
Approach: They propose a method to enhance the multilingual performance of Large Language Models by aggregating knowledge from diverse languages.
Outcome: The proposed method reduces the performance disparity across languages and offers valuable insights for further exploration.
UniMath: A Foundational and Multimodal Mathematical Reasoner (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for interpreting and processing diverse mathematical modalities are limited . existing systems are limited in interpreting complex mathematical tasks and implementing them in a multimodal manner.
Approach: They propose a multimodal mathematical reasoning system that utilizes a fine-tuned T5 model augmented with a variational autoencoder (VAE)-based image tokenizer.
Outcome: The proposed model achieves state-of-the-art performance on SVAMP, GeoQA, and TableMWP datasets and is generalized on two additional datasets.
SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark (2024.acl-short)

Copied to clipboard

Challenge: SceMQA focuses on core science subjects including Mathematics, Physics, Chemistry, and Biology.
Approach: They propose to use SceMQA to evaluate multimodal question answering at college entrance level.
Outcome: The proposed model provides specific knowledge points for each problem and detailed explanations for each answer.
Scientific Paper Extractive Summarization Enhanced by Citation Graphs (2022.emnlp-main)

Copied to clipboard

Challenge: citation graphs can be used to extract scientific papers under different conditions.
Approach: They propose a multi-granularity unsupervised summarization model that fine tunes a pre-trained encoder model on the citation graph by link prediction tasks.
Outcome: The proposed model outperforms baseline models on a public benchmark dataset.
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving (2022.findings-naacl)

Copied to clipboard

Challenge: Existing work on math word problem solvers replace real numbers with symbolic placeholders to focus on logic reasoning.
Approach: They propose to inject numerical properties into symbolic placeholders with contextualized representation learning schema to solve number representation dilemma.
Outcome: The proposed model can solve MWP problems on English and Chinese benchmarks.
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data (2026.acl-short)

Copied to clipboard

Challenge: Strong base models saturate benchmarks, resulting in weaker performance, a paradox . a new approach to Reinforcement Learning (RL) is needed to improve performance .
Approach: They propose a method that uses constrained uniform top-k sampling to flatten the local optimization landscape by sampling uniformly from constrained high-confidence candidates.
Outcome: Experiments show that the proposed approach prevents policy degeneration and boosts out-of-domain generalization.
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to watermark low-entropy content are expensive and risky . IE reduces parameter size by 99% while achieving performance on par with state-of-the-art methods .
Approach: They propose a logit-based watermarking paradigm that uses entropy-based features to predict whether the next token is high or low.
Outcome: The proposed method reduces parameter size by 99% while achieving performance on par with state-of-the-art methods.
Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used to remove harmful knowledge and undesirable capabilities.
Approach: They propose a framework that leverages Cognitive Diagnosis Modeling to evaluate LLM unlearning.
Outcome: The proposed framework enhances evaluation and facilitates removal of harmful abilities.
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs (2026.findings-acl)

Copied to clipboard

Challenge: prevailing taxonomies neglect robustness and honesty, yielding safer-on-paper but less useful systems.
Approach: They propose a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference.
Outcome: The proposed model maintains safety while reducing over-refusal.
Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches for distilling large language models into smaller, more efficient student models are based on educational science principles such as knowledge tracing and personalized learning.
Approach: They propose a method for distilling large language models into smaller, more efficient student models that are aligned with educational science principles such as knowledge tracing and personalized learning.
Outcome: The proposed approach outperforms LLMs on three benchmarks while employing significantly fewer parameters.
Data-Efficient Language Shaped Few-shot Image Classification (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have shown that language is helpful guider for image understanding by neural networks.
Approach: They propose a language-shaped learning method that makes the best use of the few-shot images and the language available only in training.
Outcome: The proposed method outperforms state-of-the-art methods on a few-shot dataset with limited training data.
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in LLMs unlearning have shown remarkable success in removing unwanted data-model influences while preserving the model’s utility for legitimate knowledge.
Approach: They propose a Selected-Expert Unlearning Framework (SEUF) that combines expert attribution and an anchor loss to ensure controlled unlearning.
Outcome: Experiments show that the proposed framework improves forget quality and model utility by 35% on MoE LLMs across benchmarks and LLM architectures compared to standard unlearning algorithms .
Few-shot Low-resource Knowledge Graph Completion with Reinforced Task Generation (2023.findings-acl)

Copied to clipboard

Challenge: Existing few-shot learning-based models have difficulty alleviating the long-tail issue on low-resource KGs because of the lack of training tasks.
Approach: They propose a few-shot low-resource knowledge graph completion framework that generates and selects beneficial few- shot tasks that complement current tasks.
Outcome: The proposed framework is based on several real-world knowledge graphs and validates on multiple domains.
Compositional Mathematical Encoding for Math Word Problems (2023.findings-acl)

Copied to clipboard

Challenge: Existing MWP encoders work in a unimodal setting and map problem description to latent representation, then for decoding.
Approach: They propose a Compositional Math Word Problem Solver which maps problem description to latent representation and decodes it in an interactive way.
Outcome: Extensive experiments show that the proposed model outperforms state-of-the-art models on public benchmarks.
RAt: Injecting Implicit Bias for Text-To-Image Prompt Refinement Models (2024.emnlp-main)

Copied to clipboard

Challenge: Text-to-image prompt refinement (T2I-Refine) aims to rephrase or extend an input prompt with more descriptive details that can be leveraged to generate images with higher quality.
Approach: They develop an adversarial prompt attacking framework that implicitly attacks input prompts with intentional adversarials to generate images with higher quality.
Outcome: The proposed framework can implicitly attack input prompts with implicit concept biases to generate images with higher quality and explicit visual bias towards the target group.
PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly integrated into real-world decision-making, but their ability to comprehend and reason about policy-related content remains underexplored.
Approach: They propose a bilingual benchmark evaluating policy comprehension comprising 21K cases across a broad spectrum of policy areas.
Outcome: The proposed model shows stronger performance on application-oriented policy tasks than on memorization or conceptual understanding, and yields the highest accuracy on structured reasoning tasks.
Analogical Math Word Problems Solving with Enhanced Problem-Solution Association (2022.emnlp-main)

Copied to clipboard

Challenge: Analogical reasoning has long been used in mathematical education, as it enables students to apply common relational structures of mathematical situations to solve new problems.
Approach: They propose to leverage analogical MWPs to advance the solver’s generalization ability across different kinds of MWps.
Outcome: The proposed model has a stronger generalization ability in solving difficult MWPs due to the analogical learning from easy MWPS.
Quest2DataAgent: Automating End-to-End Scientific Data Collection (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing approaches for data collection are labor-intensive and dependent on domain expertise.
Approach: They propose a general-purpose multi-agent framework for automating scientific data collection workflows.
Outcome: The proposed framework improves data relevance, usability, and time efficiency over existing methods.
RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems (2026.acl-demo)

Copied to clipboard

Challenge: Recent advances in large language model (LLM) agents have accelerated deployment of multi-agent systems for complex tasks.
Approach: They propose an open-source toolkit for instantiating, probing, and measuring emergent risks in LLM-based multi-agent systems under controlled conditions.
Outcome: The proposed toolkit is based on a structured topology–environment–protocol–agent–task quintuple enabling reproducible studies of how communication structure, coordination mechanisms, and incentives shape system-level risks.
Improving the Robustness of Summarization Systems with Dual Augmentation (2023.acl-long)

Copied to clipboard

Challenge: Experimental results show that state-of-the-art summarization models have a significant decrease in performance on adversarial and noisy test sets.
Approach: They propose a SummAttacker approach to generate adversarial samples based on pre-trained language models that can generate word-level synonym substitution and noise.
Outcome: The proposed model performs better on noisy, attacked, and clean datasets than baseline models and is more robust on noisy and attacked datasets.
MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods focus on specializing LMs in mathematical reasoning and rely on knowledge distillation.
Approach: They propose a multi-view fine-tuning method that exploits existing mathematical problem datasets with diverse annotation styles.
Outcome: The proposed method outperforms existing methods that rely heavily on LLM teachers . it grants models generalization ability across views and datasets, and the capability to learn from inaccurate or incomplete data.
Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large language models have achieved remarkable success in Natural Language Processing, yet their cross-lingual consistency remains a significant challenge.
Approach: They propose a method to identify cross-lingual weaknesses in Large Language Models . they construct bilingual question pairs that expose performance discrepancies between English and target languages .
Outcome: The proposed method uncovers over 50% accuracy drops in target languages across models.
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks that rely on final-answer accuracy fail to capture the quality of the reasoning process.
Approach: They propose a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.
Outcome: The proposed framework assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.
A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Multimodal mathematical Reasoning (MMR) has attracted increasing attention for its ability to solve mathematical problems involving both textual and visual modalities.
Approach: They review the theoretical frameworks of multimodal reasoning and examine the challenges they face in visual math tasks.
Outcome: The proposed models can solve problems involving both textual and visual modalities.
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Understanding how jailbreaking works remains limited, hindering the development of effective defense strategies.
Approach: They propose a new mechanism that adaptively constrains activations within the safety boundary and propose 'Activation Boundary Defense' to enhance its effectiveness.
Outcome: The proposed defense achieves an average Defense Success Rate (DSR) of over 98% against various jailbreak attacks, with less than 2% impact on the model’s general capabilities.
CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP (2025.acl-long)

Copied to clipboard

Challenge: MU has gained significant attention as a means to remove the influence of specific data from a trained model without requiring full retraining.
Approach: They propose a novel approach that disentangles and selectively forgets both visual and textual associations, ensuring that unlearning does not compromise model performance.
Outcome: Experiments on CIFAR-100, Flickr30K, and Conceptual 12M show that CLIPErase effectively removes designated associations from multimodal samples in downstream tasks while preserving model performance on retain set.
SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing AVQA methods often fail to link sound-producing objects in the video with the audio-visual information.
Approach: They introduce a source-aware semantic representation network for AVQA . they use source-wise learnable tokens to capture and align audio-visual elements with the question .
Outcome: The proposed model outperforms state-of-the-art models on the Music-AVQA and AVQA-Yang datasets.
Defending Jailbreak Prompts via In-Context Adversarial Game (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications, but concerns regarding their security persist.
Approach: They propose an adversarial game that leverages agent learning to extend knowledge to defend against jailbreaks.
Outcome: The proposed game shows that LLMs safeguarded by ICAG exhibit significantly reduced jailbreak success rates across various attack scenarios.
ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture (2022.emnlp-main)

Copied to clipboard

Challenge: ArtELingo is a benchmark and dataset designed to encourage work on diversity across languages and cultures.
Approach: They introduce a benchmark and dataset designed to encourage work on diversity across languages and cultures.
Outcome: The new benchmark and dataset compared artELingo annotations across languages and cultures and found that diversity improves the performance of baseline models.

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