Papers by Zijie Wang

22 papers
Progra: Progress-Aware Reinforcement Learning for Multi-Turn Function Calling (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for multi-turn function calling are limited by redundancy and lack explicit integration of progress awareness into training.
Approach: They propose a framework that explicitly integrates progress awareness into LLM training for multi-turn function calling.
Outcome: Empirical results show that Progra outperforms existing methods on two public benchmarks.
From Outcome to Process: Optimizing MoE Load Balancing with MCTS (2026.findings-acl)

Copied to clipboard

Challenge: Existing balancing strategies focus on constraining the final distribution of expert usage, but overlook the routing decisions made at each layer.
Approach: They propose a three-stage framework that leverages process-level rewards to guide balanced expert routing.
Outcome: Extensive experiments show that LayerMoE improves the performance of state-of-the-art LoRA-MoA baselines, yielding an average accuracy gain of 1.39%.
On the Consistency of Commonsense in Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluations of commonsense for large language models focus on downstream knowledge tasks, failing to probe whether LLMs truly understand and utilize knowledge or merely memorize it.
Approach: They propose to automatically construct a large benchmark named CoCo which measures LLMs’ knowledge memorization, comprehension, and application and examines the consistency between these tasks.
Outcome: The proposed benchmark systematically assesses LLMs’ knowledge memorization, comprehension, and application and examines the consistency between these tasks.
Acquisition and Application of Novel Knowledge in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for constructing new datasets rely on timestamps or simple templates that do not accurately reflect the real world.
Approach: They propose a knowledge dataset construction approach that simulates biological evolution using knowledge graphs to generate synthetic entities with diverse attributes.
Outcome: The proposed framework outperforms knowledge augmentation methods by 3.3%-38%.
Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to predict missing facts in knowledge graphs are limited in language alignment . SS-AGA uses seed alignment as an edge type to fuses all KGs as a whole graph .
Approach: They propose a self-supervised adaptive graph alignment method that fuses all KGs as a whole graph by regarding alignment as 'a new edge type' they propose SS-AGA method that uses relation-aware attention weights to capture potential alignment pairs in a new paradigm.
Outcome: The proposed method can predict missing facts in a knowledge graph (KG) but language alignment is scarce and new alignment identification is noisy.
Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to embed knowledge graphs have ignored the fact that they contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities.
Approach: They propose a novel geometric representation that jointly embeds the two views of a KG using dual geometric representations.
Outcome: Experiments on the public DBpedia KG and a newly-created industrial KG show the proposed method works well.
Wordflow: Social Prompt Engineering for Large Language Models (2024.acl-demos)

Copied to clipboard

Challenge: Large language models (LLMs) require well-crafted prompts for effective use.
Approach: They propose a social prompt engineering paradigm that leverages social computing techniques to facilitate collaborative prompt design.
Outcome: The proposed paradigm leverages social computing techniques to facilitate prompt design.
FedMABench: Benchmarking Mobile GUI Agents on Decentralized Heterogeneous User Data (2025.emnlp-main)

Copied to clipboard

Challenge: Mobile GUI agents have attracted tremendous research participation recently. traditional approaches to mobile agent training rely on centralized data collection.
Approach: They propose a benchmark for federated training and evaluation of mobile GUI agents . they find that federation algorithms consistently outperform local training .
Outcome: The first benchmark for federated training and evaluation of mobile GUI agents is released . it features 6 datasets with 30+ subsets, 8 federation algorithms, 10+ base models, and over 800 apps across 5 categories .
Streaming Hallucination Detection in Long Chain-of-Thought Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Long chain-of-thought reasoning improves performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps.
Approach: They propose to treat step-level hallucination judgments as local observations and introduce a cumulative prefix-level signal that tracks the global evolution of the reasoning state over the entire trajectory.
Outcome: The proposed method enables streaming hallucination detection in long CoT reasoning, providing real-time, interpretable evidence.
Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Negation is a common and important semantic feature in natural language, yet Large Language Models struggle when negation is involved in natural learning tasks.
Approach: They propose to augment existing corpora with negation by automatically augmenting existing ones with negations by combining multiple triples with if-then relations.
Outcome: The proposed approach yields two new corpora containing over 2M triples with if-then relations.
On the Role of Discriminative Models in Generative Relation Extraction (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for relation extraction (RE) are discriminative and generative . previous studies show that discriminative models can support generative RE .
Approach: They propose a framework that leverages discriminative models to produce a top-k set of candidate relations and integrates this knowledge into generative models via in-context or prompt learning.
Outcome: The proposed framework achieves state-of-the-art on five widely used RE benchmarks.
FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference (2025.findings-emnlp)

Copied to clipboard

Challenge: Key-Value (KV) cache reading latency increases with context lengths hindering LLM inference . important tokens are sparsely distributed across the long context, making existing retrieval inaccurate .
Approach: They propose a method to retain a small fraction of KV cache based on token importance . important tokens are often sparsely distributed across the long context .
Outcome: The proposed method reduces decoding latency by 1.2 to 1.5.
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach: They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome: The proposed framework outperforms baseline methods in real-time and in real applications.
Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains (2024.findings-naacl)

Copied to clipboard

Challenge: Existing models for yes-no questions are challenging, but they still face challenges.
Approach: They propose an approach grounded on distant supervision and blended training to quickly adapt to a new dialogue domain.
Outcome: The proposed approach improves F1 performance in movie scripts, tennis interviews, and airline customer service domains.
RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services (2025.emnlp-industry)

Copied to clipboard

Challenge: Social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement.
Approach: They propose a domain-specific LLM to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for social networking services.
Outcome: The proposed model achieves an average improvement of 14.02% across 8 major tasks and 7.56% in bilingual evaluation benchmark, compared with baseline models.
Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection (2025.acl-long)

Copied to clipboard

Challenge: Existing work has been using decoding-free candidate selection methods to obtain candidate probability from initial output logits over vocabulary.
Approach: They propose to evaluate a set of tasks using decoding-free candidate selection methods on a comprehensive set of questions.
Outcome: The proposed methods are evaluated on a set of tasks including five multiple-choice QA tasks with a small candidate pool and four clinical decision tasks with 10k+ options.
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Copied to clipboard

Challenge: AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach: They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome: AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.
Interpreting Indirect Answers to Yes-No Questions in Multiple Languages (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing models for Yes-no questions skip polar keywords and instead use long explanations that must be interpreted.
Approach: They propose a distant supervision approach to collect training data and show that direct answers are useful to train models to interpret indirect answers.
Outcome: The proposed model achieves a 68% to 76% F1-score on multilingual Question-Answering benchmarks.
Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for relational triple extraction (RTE) are unnatural and recast RTE tasks to text-to-text prompting formats.
Approach: They propose a tabular prompting for RTE which frames RTE task into a table generation task and propose an instructive in-context learning which only selects and annotates samples considering triple semantics in massive unlabeled samples.
Outcome: The proposed prompting for RTE with TableIE achieves state-of-the-art performance compared to other methods . the proposed prompts are based on off-the shelf LLMs and are scalable to multiple scenarios .
Identifying and Answering Questions with False Assumptions: An Interpretable Approach (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate misleading answers because of hallucinations . despite their capabilities, LLMs suffer from hallucinisms, which leads to unfaithful answers .
Approach: They propose a method to identify and answer questions with false assumptions . they first investigate whether the problem reduces to fact verification . then, they leverage external evidence to mitigate hallucinations .
Outcome: The proposed approach reduces the problem to fact verification and provides interpretable answers by pinpointing the false assumptions.
SEMIROUTER: Sparse-Data Enhanced Routing for Adaptive Multi-LLM System (2026.eacl-long)

Copied to clipboard

Challenge: Existing routing methods suffer from poor scalability and dependence on datasets for training . energy footprint is also considered in the decision to implement our new LLM routing framework .
Approach: They propose a new LLM routing framework that dynamically allocates queries to the most appropriate LLM.
Outcome: The proposed method improves data efficiency, adaptability, and routing accuracy compared to existing methods.
CMNEE:A Large-Scale Document-Level Event Extraction Dataset Based on Open-Source Chinese Military News (2024.lrec-main)

Copied to clipboard

Challenge: Current research focuses on the general news or financial domains, with relatively few studies for military domain.
Approach: They propose to annotate Chinese military news events from documents using a schema for the military domain.
Outcome: The proposed dataset is large-scale, document-level open-source for the military domain . it contains 17,000 documents and 29,223 events, which are all manually annotated .

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