Papers by Zhe Hu

18 papers
SP3: Enhancing Structured Pruning via PCA Projection (2024.findings-acl)

Copied to clipboard

Challenge: Structured pruning is a widely used technique for reducing the size of pre-trained language models, but current methods overlook the potential of compressing the hidden dimension d in PLMs.
Approach: They propose a structured pruning approach that projectes features into a space defined by principal components before masking the hidden dimension d in pre-trained language models.
Outcome: Experiments on benchmarks show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy.
VIVA+: Human-Centered Situational Decision-Making (2025.findings-emnlp)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) show promising results in complex, human-centered environments, yet evaluating their capacity for nuanced, humanlike reasoning and decision-making remains challenging.
Approach: They introduce VIVA+, a cognitively grounded benchmark for evaluating the reasoning and decision-making of MLLMs in human-centered situations.
Outcome: The VIVA+ model is based on 1,317 real-world situations paired with 6,373 multiple-choice questions . it consists of three core abilities for decision-making: (1) Foundational Situation Comprehension, (2) Context-Driven Action Justification, and (3) Reflective Reasoning.
MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective (2022.emnlp-main)

Copied to clipboard

Challenge: Recent pre-trained language models have produced impressive results, but there is still a gap between human written texts and machine-generated outputs.
Approach: They propose a multi-task training strategy for long text generation grounded on the cognitive theory of writing.
Outcome: The proposed model achieves better results on three open-ended generation tasks than baselines.
E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Challenge: Named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty.
Approach: They propose to introduce two uncertainty-guided loss terms to the conventional EDL and a series of uncertainty-guiding training strategies to solve these challenges.
Outcome: The proposed method achieves better OOV/OOD detection performance and generalization ability on OOV entities compared to state-of-the-art methods.
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Copied to clipboard

Challenge: Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach: They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome: The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .
Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation (2025.coling-main)

Copied to clipboard

Challenge: Writing arguments requires integrating high-level beliefs from various perspectives . current language models generate outputs autoregressively, resulting in limited diversity and coherence .
Approach: They propose a persona-based multi-agent framework for argument writing that integrates beliefs from different perspectives into a coherent narrative.
Outcome: The proposed framework generates more diverse arguments by both automatic and human evaluations.
Context-Aware Interaction Network for Question Matching (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models focus on word-level local matching and neglect the importance of contextual information.
Approach: They propose a context-aware interaction network to properly align two sequences and infer their semantic relationship by using gate fusion layers.
Outcome: The proposed model can accurately align two sequences and infer their semantic relationship on two question matching datasets.
VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values (2024.emnlp-main)

Copied to clipboard

Challenge: Recent large vision language models (VLMs) have demonstrated remarkable intelligence and proficiency across diverse tasks.
Approach: They propose a benchmark for VIsion-grounded decision-making driven by human VA.
Outcome: The proposed model can make decisions under a vision-depicted situation using human values and human values.
Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? (2025.findings-emnlp)

Copied to clipboard

Challenge: Despite significant progress in multimodal language models, it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models.
Approach: They propose to assess vision-language models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.
Outcome: The proposed benchmark assesses the models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.
Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding (2026.eacl-long)

Copied to clipboard

Challenge: Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts.
Approach: They propose a lightweight auxiliary model trained with a GAE-inspired objective to predict final instruction-following quality from partial generations.
Outcome: The proposed model achieves 10 points improvement in CLAP score over baseline AR models while maintaining computational parity with best-of-N decoding.
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for text generation still suffer from incoherence problems . Neural sequence-to-sequence (seq2sequ) models generate fluent results .
Approach: They propose a novel generation framework that leverages autoregressive self-attention mechanism to conduct content planning and surface realization dynamically.
Outcome: The proposed framework outperforms baseline models and generates more coherent texts with richer contents.
Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers (2025.emnlp-main)

Copied to clipboard

Challenge: Autoregressive language models excel in text-to-audio generation, but lag behind diffusion models by a non-trivial margin.
Approach: They propose a framework that integrates multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning.
Outcome: The proposed framework outperforms existing LM-based and diffusion-based systems in audio synthesis.
Argument Generation with Retrieval, Planning, and Realization (P19-1)

Copied to clipboard

Challenge: a novel argument generation framework is used to generate counter-arguments . CANDELA uses a text planning decoder to retrieve arguments of different perspectives .
Approach: They propose a powerful retrieval system and a novel two-step argument generation framework . they use a retrieval-based retrieval platform indexed with 12 million articles from Wikipedia .
Outcome: The proposed framework yields higher BLEU, ROUGE, and METEOR scores than state-of-the-art models.
Analogical Reasoning on Chinese Morphological and Semantic Relations (P18-2)

Copied to clipboard

Challenge: Analogical reasoning is effective in capturing linguistic regularities.
Approach: They propose to use Chinese lexical knowledge to build an analogical reasoning task using a large dataset.
Outcome: The proposed dataset proves to be reliable benchmark for evaluating Chinese word embeddings.
An Entity-Driven Framework for Abstractive Summarization (D19-1)

Copied to clipboard

Challenge: Popular neural summarization models produce incoherent and unfaithful summaries . however, their outputs are often incohérent and incoerent .
Approach: They propose a system for ENtity-drivEn Coherent Abstractive summarization framework that leverages entity information to generate informative and coherent abstracts.
Outcome: The proposed framework outperforms existing state-of-the-art models on New York Times and CNN/Daily Mail datasets.
KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for parameter-efficient finetuning (PEFT) are limited and only finetune a small number of parameters using limited instruction data.
Approach: They propose a method that inserts an adaptation layer into an LLM to integrate embeddings of entities appearing in the input text.
Outcome: The proposed method can activate parameterized knowledge in an LLM without changing its parameters or input prompts.
iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation (2025.acl-demo)

Copied to clipboard

Challenge: Existing approaches to role-playing emotional companion products lack sustained personalization and contextual adaptability, limiting their effectiveness in real-world settings.
Approach: They propose a virtual pet agent that can enhance user engagement through rich, dynamic pet behaviors and interactions tailored to individual preferences.
Outcome: The proposed system has been deployed in a real-world, non-commercial product for 200 days and has demonstrated its effectiveness in practical applications.
Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing Automated Essay Scoring (AES) methods focus on sentence-level features, whereas Large Language Models (LLMs) are sensitive to conventions & accuracy, language complexity, and organization.
Approach: They propose to use large language models to aid in decision-making . they propose to analyze the reasoning of neural models by analyzing sentence-level features.
Outcome: The proposed method improves understanding of neural approaches to Automated Essay Scoring (AES) and can also apply to other domains seeking transparency in model-driven decisions.

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