Papers by Hang Wu

29 papers
From Selection to Refinement: Iterative Optimization for Instruction Data (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to optimize instruction tuning datasets face two main challenges: unreasonable pruning of potentially valuable low-quality data and the persistence of noise or semantic drift during revision.
Approach: They propose an automated iterative framework for instruction data optimization that prunes low-quality data and refines low quality data using feedback-driven iteration.
Outcome: The proposed framework outperforms state-of-the-art methods on seven public benchmark datasets with high data efficiency.
Length Generalization of Causal Transformers without Position Encoding (2024.findings-acl)

Copied to clipboard

Challenge: Besides Transformers without position encodings, the success of NoPE provides a new way to overcome the challenge of generalizing to longer sentences.
Approach: They propose a parameter-efficient tuning for searching attention heads’ best temperature hyper-parameters, which substantially expands NoPE’s context size.
Outcome: The proposed tuning significantly expands NoPE's context size, allowing it to generalize to longer sentences with state-of-the-art generalization algorithms.
MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have improved generation and reasoning capabilities compared to traditional BERT-sized models due to massive number of parameters and extensive pre-training on vast textual corpora.
Approach: They propose a unified post-hoc adapter for test-time adaptation of large language models . they propose to fine-tune only a small BERT-sized adapter to rank candidate LLMs .
Outcome: The proposed adapter improves performance on four biomedical tasks without requiring computational resources or sharing data with third parties.
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis (2026.findings-acl)

Copied to clipboard

Challenge: SynthRL synthesizes over 3.3K additional verifiable, challenging questions from approximately 8K seed samples.
Approach: They propose a scalable and guaranteed pipeline for automatic data scaling in reasoning-oriented RL training.
Outcome: The proposed pipeline synthesizes over 3.3K additional verifiable, challenging questions from approximately 8K seed samples.
EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records (2024.emnlp-main)

Copied to clipboard

Challenge: EHRAgent enables clinicians to interact with EHRs using natural language . reliance on rule-based conversion systems often necessitates additional training or effort from data engineers.
Approach: They propose a large language model agent that generates and executes code in natural language to facilitate clinicians in directly interacting with EHRs.
Outcome: The proposed agent outperforms the strongest baseline by up to 29.6% in success rate on three real-world EHR datasets.
Towards Robust Few-Shot Relation Classification: Incorporating Relation Description with Agreement (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to recognize relational relationships with a few support samples are limited for unlimited queries.
Approach: They propose a simple but effective framework that uses relation descriptions as external knowledge to enhance the model’s comprehension of the relation semantics.
Outcome: The proposed framework outperforms strong baselines while being robust against various NOTA rates.
BiKT: Enabling Bidirectional Knowledge Transfer Between Pretrained Models and Sequential Downstream Tasks (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing frameworks adapt from initial pretrained model to each downstream task directly, but ignore sequential nature of downstream tasks and feedback effect on pretrained models.
Approach: They propose a framework to enable bidirectional knowledge transfer between pretrained models and downstream tasks in rounds.
Outcome: The proposed framework improves on 9 GLUE datasets and 6 SuperGLUEs.
Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on what to generate but ignore what not to generate . a template-agnostic method boosts original learning and reduces mistakes simultaneously .
Approach: They propose a template-agnostic method to control the token-level generation . they introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models .
Outcome: The proposed method boosts original learning and reduces mistakes simultaneously on four public datasets.
Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion (2024.acl-long)

Copied to clipboard

Challenge: Current methods embed factual knowledge into continuous vector space and apply geometric operations to learn potential patterns in temporal knowledge graphs.
Approach: They propose a temporal knowledge graph completion method that uses two geometric operations to learn missing facts in temporal graphs.
Outcome: The proposed method significantly outperforms existing temporal knowledge graph embedding models.
MUR: Momentum Uncertainty guided Reasoning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for optimizing reasoning quality are limited by overthinking.
Approach: They propose a method that allocates thinking budgets to critical reasoning steps by tracking and aggregating step-wise uncertainty over time.
Outcome: The proposed method reduces computation by over 45% on average while improving accuracy by 0.33–3.46%.
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.
XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser (2025.coling-main)

Copied to clipboard

Challenge: Document AI parsing semi-structured image form is a key information extraction task.
Approach: They propose a multimodal and multilingual semi-structured FORM PARSER which integrates SER and relation extraction into a unified framework.
Outcome: The proposed framework achieves up to 1.79% improvement on RE tasks in multilingual and zero-shot settings.
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for enhancing LLM reasoning rely on supervisory signals . current methods rely heavily on outcome supervision and auxiliary reward models .
Approach: They propose a gen-eralizable and purely unsupervised self-training framework to enhance LLM reasoning without supervision.
Outcome: The proposed framework improves LLM reasoning without supervision without external supervision.
Text-to-Table: A New Way of Information Extraction (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for information extraction are not well understood . text-to-table is a problem that aims to extract information from text data .
Approach: They propose a new problem setting of information extraction, called text-to-table . they formalize text- to-table as a sequence-tosequence problem .
Outcome: The proposed method outperforms existing methods on text-to-table tasks.
ImF: Embedding an Implicit Fingerprint in Your Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Training and serving large language models (LLMs) is resource-intensive, making reliable intellectual property protection and black-box ownership verification increasingly important.
Approach: They propose a method to inject a small set of secret query–response behaviors into model fingerprinting . they encode ownership information into a natural-looking target response and derive a semantically aligned query .
Outcome: The proposed fingerprints improve stealthiness and remain verifiable under model updates and deployment-time prompt interventions.
GLGE: A New General Language Generation Evaluation Benchmark (2021.findings-acl)

Copied to clipboard

Challenge: Multi-task benchmarks focus on a range of Natural Language Understanding (NLU) tasks without considering the Natural Language Generation (NLG) models.
Approach: They propose a multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks.
Outcome: The proposed benchmarks are based on GLUE and Su-perGLUE for English and several other languages.
Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations (2024.acl-long)

Copied to clipboard

Challenge: Currently, many benchmarks evaluate the commonsense reasoning of large language models (LLMs), but most are English-based, limiting non-English evaluations.
Approach: They propose to use Chinese commonsense reasoning to evaluate LLMs' commonsensing ability.
Outcome: The proposed benchmark covers both globally known and Chinese-specific commonsense reasoning abilities and can be used as a reference for future research.
Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models for generating mathematical word problems are lacking in educational assessment.
Approach: They propose an end-to-end neural model to generate diverse mathematical word problems from commonsense knowledge graph and equations.
Outcome: The proposed model outperforms the SOTA models in terms of evaluation metrics and topic relevance.
BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored.
Approach: They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases.
Outcome: The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods.
Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation (2022.emnlp-main)

Copied to clipboard

Challenge: Recent work on aspect sentiment quad prediction (ASQP) uses a template to extract aspect quadruplets from review sentences.
Approach: They propose to use a pre-trained language model to select proper orders from a template order perspective to improve aspect sentiment quad prediction.
Outcome: The proposed method outperforms state-of-the-art methods significantly in low-resource settings.
ZeroGen: Efficient Zero-shot Learning via Dataset Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate training data with pre-trained language models have been found effective in various scenarios.
Approach: They propose an unsupervised zero-shot learning method that generates a dataset from scratch and trains a tiny task model under supervision of the synthesized dataset.
Outcome: The proposed method is annotated-free and efficient, but can provide useful insights from the perspective of data-free model-agnostic knowledge distillation and unreferenced text generation evaluation.
Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Event extraction is a task in natural language processing that involves identifying and extracting event information from unstructured text.
Approach: They propose a paradigm that combines schema paraphrasing with schema retrieval-augmented generation.
Outcome: The proposed paradigm retrieves paraphrased schemas and accurately generates targeted structures.
DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: DiMo-GUI is a training-free framework for GUI grounding that splits input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.
Approach: They propose a training-free framework for GUI grounding that leverages two core strategies: dynamic visual grounding and modality-aware optimization.
Outcome: The proposed framework splits the input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.
Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Backdoor-based LLM fingerprinting is a promising solution for intellectual property protection . however, the vulnerability of existing LLMs for the ensemble scenario is unexplored .
Approach: They propose two new fingerprinting attack methods to assess the robustness of LLM fingerprinting by token filter attack and sentence verification attack.
Outcome: The proposed methods inhibit the fingerprint response while maintaining ensemble performance.
𝜙-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation (2025.acl-long)

Copied to clipboard

Challenge: Existing inference-time optimization strategies address the shortsightedness of auto-regressive generation, but the vast search space leads to excessive exploration and insufficient exploitation.
Approach: They propose a decoding strategy that approximates two distributions via foresight and clustering to provide an efficient estimation of step value.
Outcome: The proposed decoding strategy outperforms strong baselines in performance and efficiency.
GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Current methods for instruction generation depend on privileged inputs such as semantic maps, landmark annotations, and panoramic views.
Approach: They propose a task that generates coherent navigation instructions from egocentric visual observations.
Outcome: The proposed task generates coherent navigation instructions from egocentric visual data . the proposed task improves performance over state-of-the-art methods in BLEU-4 and CIDEr scores .
CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors (2023.acl-long)

Copied to clipboard

Challenge: Large language models pre-trained on massive corpora have shown impressive few-shot learning ability on many NLP tasks.
Approach: They propose to recast structured output in the form of code instead of natural language and use generative LLMs of code to perform IE tasks.
Outcome: The proposed method outperforms fine-tuning moderate-size pre-trained models and prompting NL-LLMs under few-shot settings.
ECoK: Emotional Commonsense Knowledge Graph for Mining Emotional Gold (2024.findings-acl)

Copied to clipboard

Challenge: Existing knowledge graphs focus on the representation and reasoning of general factual knowledge, while there are significant deficiencies in the understanding and reasoning for emotional knowledge.
Approach: They propose a commonsense knowledge graph that can be used to represent emotional knowledge by combining theories from psychology, cognitive science, and linguistics.
Outcome: The proposed model surpasses GPT-4-Turbo in the emotion-related tasks.
CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations (2021.emnlp-main)

Copied to clipboard

Challenge: Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms.
Approach: They propose a cross-modal transformer for audio-and-language that learns inter-modal connections between audio and language through two proxy tasks on a large amount of audio- and-language pairs.
Outcome: The proposed model improves on multiple audio-and-language tasks and can be used in fine-tuning phase.

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