Papers by Zhen Yu

36 papers
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing defenses, including post-training alignment and prompt engineering, struggle with adaptability to out-of-distribution (OOD) attacks.
Approach: They propose an adversarial game-based defense method that dynamically adjusts LLMs’ internal representations to achieve a balanced trade-off between helpfulness and harmlessness.
Outcome: The proposed method improves LLMs’ safety over all baselines.
CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios (2025.emnlp-main)

Copied to clipboard

Challenge: a number of tools are used to perform complex tasks, but the tool utilization process can cause errors.
Approach: They propose a critique evaluation benchmark for tool learning that analyzes function-calling errors on tool evaluation benchmarks.
Outcome: The proposed critique evaluation benchmark holds diverse tool-use errors with varying complexities, which better reflects real-world scenarios.
Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are fast but require expensive pre-training . a new approach to scale large language models into MoEs reduces inference costs .
Approach: They propose an analytical post-training framework that rapidly restructures FFNs into sparse MoE architectures using only a small calibration dataset.
Outcome: The proposed framework outperforms existing methods on a small calibration dataset.
Argumentation Mining on Essays at Multi Scales (2020.coling-main)

Copied to clipboard

Challenge: Argumentation mining on essays is a new task in natural language processing.
Approach: They propose a multi-scale argumentation mining model which aims to identify the types and locations of argumentation components from essay text.
Outcome: The proposed model outperforms existing models on mining all types of argumentation components on the Persuasive Essay dataset.
Beyond Verbal Cues: Emotional Contagion Graph Network for Causal Emotion Entailment (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies have focused on identifying the causes of emotions by understanding verbal contextual utterances, but this study often lacks recognizing the underlying emotional stimuli present in these utterrances.
Approach: They propose an Emotional Contagion Graph Network that simulates the impact of non-verbal emotional cues on the counterpart’s emotions.
Outcome: The proposed model is compared with state-of-the-art models on a benchmark dataset and the results are encouraging.
Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework (2025.emnlp-main)

Copied to clipboard

Challenge: Bit-flip errors (BFEs) are hardware faults where individual bits in memory or processing units are unintentionally flipped.
Approach: They propose a novel defense strategy to mitigate bit-flip errors (BFEs) they propose bfe protection and a self-correction mechanism to minimize performance degradation .
Outcome: The proposed defense strategy minimizes performance degradation while significantly improving robustness against BFEs.
Sparse Black-Box Multimodal Attack for Vision-Language Adversary Generation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing adversarial attacks using imperceptible perturbations are challenging to simulate . e-commerce product restrictions and hate speech monitoring are examples of such attacks .
Approach: They propose a black-box adversarial attack that leverages sparse perturbations to simulate adversarials exhibited by illegal merchants in the black- box scenario.
Outcome: The proposed method outperforms existing attacks and unimodal attacks by treating images and text in discrete space and outperforming existing models.
Predicting Text Preference Via Structured Comparative Reasoning (2024.acl-long)

Copied to clipboard

Challenge: Existing approaches to comparative reasoning rely on pretraining or fine-tuning models at the cost of massive human annotation and computation.
Approach: They propose a model that prompts LLMs to generate structured intermediate comparisons by proposing aspects for comparison, followed by generating textual comparisons under each aspect.
Outcome: The proposed model significantly reduces hallucination and improves consistency across various NLP tasks.
A Sequence-to-Structure Approach to Document-level Targeted Sentiment Analysis (2023.findings-emnlp)

Copied to clipboard

Challenge: Aspect-based sentiment analysis (ABSA) has received wide attention in NLP for nearly two decades . previous studies focused on sentence-level ABSA, but document-level research has not received enough attention.
Approach: They propose a Sequence-to-Structure approach to address the document-level targeted sentiment analysis task, which aims to extract the opinion targets consisting of multi-level entities from a review document and predict their sentiments.
Outcome: The proposed approach outperforms baselines on six domains on the document-level targeted sentiment analysis task.
Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification (2020.coling-main)

Copied to clipboard

Challenge: inessential words are unintentionally misjudged as attention-worthy words and assigned heavier attention weights than should be.
Approach: They propose a penalty-based method to regulate the attention learning process by integrating penalty coefficients into the computation of loss by means of overstability of attention weight distributions.
Outcome: The proposed method improves on the Penn Discourse TreeBank corpus and is competitive compared to the state-of-the-art methods.
PlotGen-Bench: Evaluating VLMs on Generating Visualization Code from Diverse Plots across Multiple Libraries (2026.findings-acl)

Copied to clipboard

Challenge: PlotGen-Bench evaluates vision-language models' ability to generate executable visualization code from plots under realistic and complex visualization requirements.
Approach: They propose a benchmark to evaluate plot-to-code generation in vision-language models . they use Matplot, Matplos, Mat3D, Mat4D, and Mat4E to evaluate their performance .
Outcome: The proposed benchmark covers 9 major categories, 30 subcategories, and 3 core tasks . it covers 2D, 3D and animated plots across 5 widely used visualization libraries.
LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning (2024.findings-acl)

Copied to clipboard

Challenge: Low-rank adaption (LoRA) is a low-level pruning method that can be expensive and slow to deploy.
Approach: They propose a low-rank adaption pruning framework that provides an accurate structured pruned model in a memory-efficient manner.
Outcome: The proposed pruning framework reduces perplexity and memory usage by 52.6% on LLaMA and T5 models while reducing memory usage.
MultiSQL: A Schema-Integrated Context-Dependent Text2SQL Dataset with Diverse SQL Operations (2024.findings-acl)

Copied to clipboard

Challenge: Text2SQL is a task that translates natural language into SQL statements.
Approach: They propose a task that translates natural language into SQL statements.
Outcome: The proposed task enables users to convert natural language into SQL statements.
Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale (2026.findings-acl)

Copied to clipboard

Challenge: a large-scale empirical dataset involving 57,954 essays from 10,195 students across 120 schools over two years is presented in this paper.
Approach: They propose a triadic collaboration system that supports K-12 writing learning . they propose linguistic expansion as a pedagogical gatekeeper and bridge .
Outcome: The proposed system improves writing quality through a strategic labor division . authors find that excessive linguistic expansion yields diminishing marginal utility .
SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: SIQ quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models.
Approach: They propose a human cognition-inspired evaluation pipeline for voice understanding large language models (LLM_Voice) that quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models.
Outcome: The proposed framework quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM_Voice.
Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks (2024.naacl-long)

Copied to clipboard

Challenge: Existing black-box attacks require thousands of queries on the target model, making them expensive in real-world applications.
Approach: They propose a new approach that guides word substitutions using prior knowledge from the training set to improve the attack efficiency.
Outcome: The proposed approach reduces query-free attack and guided search attacks by a factor of 10 500 . it improves transferability and generalization by the ensemble of the ABPens in NLP .
CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher (2026.acl-long)

Copied to clipboard

Challenge: Existing models for text understanding fail to adapt to domain shifts in real-world applications . current models do not improve themselves as they are applied to new domains .
Approach: They propose a continual test-time adaptation framework that adapts to evolving domains . they propose accumulating domains and a refine-then-filter framework to calibrate teacher predictions .
Outcome: The proposed model excels in a teacher-student framework adaptable to evolving domains.
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats (2026.acl-long)

Copied to clipboard

Challenge: Microscaling Floating-Point (MXFP) is a low-precision format for large language models (LLMs).
Approach: They conduct systematic evaluations of PTQ under Microscaling Floating-Point (MXFP) . they find that MXFP8 consistently achieves near-lossless performance .
Outcome: The proposed method achieves near-lossless performance while MXFP4 introduces substantial accuracy degradation and remains challenging.
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)

Copied to clipboard

Challenge: Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis.
Approach: They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge.
Outcome: The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks.
FocalOrder: Focal Preference Optimization for Reading Order Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for document comprehension rely on uniform supervision, resulting in a performance degradation in the intermediate sections.
Approach: They propose a framework driven by Focal Preference Optimization to detect reading order in document layouts.
Outcome: The proposed framework outperforms competing baselines and surpasses large-scale general VLMs.
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing Large language model agents rely on increasingly long interaction histories, resulting in high computational cost and limited scalability.
Approach: They propose a hierarchical reinforcement learning framework that enables step-level learning by conditioning only on single-step transitions rather than full interaction histories.
Outcome: The proposed framework outperforms baselines on ScienceWorld and ALFWorld benchmarks in terms of performance and generalization while reducing token usage.
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing LLMs demonstrate powerful capabilities between tasks, but can they make sequential decisions?
Approach: They propose to evaluate sequential decision-making capability of large language models (LLMs) using novel metrics based Monte Carlo methods.
Outcome: The proposed benchmark improves sequential decision-making performance compared to the vanilla LLM player.
ManCC: A Task-Anchored Benchmark for Manchu–Classical Chinese Cross-Lingual Modeling (2026.findings-acl)

Copied to clipboard

Challenge: Mainstream research in natural language processing has focused on high-resource and modern languages.
Approach: They propose a task-anchored benchmark for Manchu–Classical Chinese translation . they use a parallel corpus of 16,627 sentence pairs to evaluate the model .
Outcome: The proposed benchmarks show that linguistic differences influence performance and broader language coverage facilitate low-resource transfer.
D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat (2022.emnlp-main)

Copied to clipboard

Challenge: Existing human-machine dialogue systems are not able to provide diagnostic information for depression diagnosis due to stigma associated with mental illness.
Approach: They propose to construct a Chinese Dialogue Dataset for depression-diagnosis-oriented chat based on clinical depression diagnostic criteria.
Outcome: The proposed system can be used to diagnose depression using a Chinese Dialogue Dataset.
Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants’ Question-Answering in Asynchronous Learning Environments (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing assessments rely on surface-level metrics and lack sufficient grounding in educational theory . a new framework is proposed to evaluate VTAs in asynchronous learning environments .
Approach: They propose a pedagogically-oriented evaluation framework tailored to asynchronous forum discussions . they construct classifiers using expert annotations of VTA responses on a diverse set of forum posts .
Outcome: The proposed evaluation framework is rooted in learning sciences and tailored to asynchronous forum discussions.
PathwiseRAG: Multi-Dimensional Exploration and Integration Framework (2025.emnlp-main)

Copied to clipboard

Challenge: Existing retrieval-augmented generation systems employ rigid retrieval strategies . static retrieval produces knowledge blind spots, missing connections between quantum algorithms and encryption vulnerabilities .
Approach: PathwiseRAG addresses these challenges through intent-aware strategy selection . it constructs a directed acyclic graph of interconnected sub-problems and explores multiple reasoning trajectories .
Outcome: The proposed framework achieves higher accuracy and better reliability than current systems.
TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing textual adversarial attacks use gradient or prediction confidence to generate adversarials, making it hard to be deployed in real-world applications.
Approach: They propose a textual adversarial attack that randomly perturbs lots of words to craft an adversarial example.
Outcome: The proposed attack outperforms existing hard-label attacks in terms of attack performance and adversary quality.
Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation (2024.findings-naacl)

Copied to clipboard

Challenge: Emotion Recognition in Conversation (ERC) is a task that aims to identify the emotions behind each utterance in a conversation.
Approach: They propose an Emotion-Anchored Contrastive Learning framework that generates more distinguishable utterance representations for similar emotions.
Outcome: The proposed framework achieves state-of-the-art on similar emotions and performs well on similar ones.
OpenUE: An Open Toolkit of Universal Extraction from Text (2020.emnlp-demos)

Copied to clipboard

Challenge: a large number of natural language processing tasks focus on token-level or sentence-level understandings.
Approach: They propose an open-source and extensible toolkit for various extraction tasks . they deploy an online demo with restful APIs to support real-time extraction .
Outcome: The proposed model can be used to extract information from text without training and deployment.
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition (2020.coling-main)

Copied to clipboard

Challenge: Existing models for discourse relation recognition use self-attention and interactive-attention mechanisms.
Approach: They develop a propagative attention learning model using a cross-coupled two-channel network.
Outcome: The proposed model improves on the baseline models on a Penn Discourse Treebank.
Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in natural language processing (NLP) have witnessed the remarkable capabilities of Large Language Models (LLMs).
Approach: They propose an Explanation-Aware Soft Ensemble framework to empower in-context learning with Large language models.
Outcome: The proposed framework can be used to enhance in-context learning on seven natural language understanding tasks and four varying-size LLMs.
Continual Named Entity Recognition without Catastrophic Forgetting (2023.emnlp-main)

Copied to clipboard

Challenge: Named Entity Recognition (CNER) is a burgeoning area of research . a new paradigm has ushered NER into a non-entity type at the current step t .
Approach: They propose a pooled feature distillation loss that skillfully navigates the trade-off between retaining knowledge of old entity types and acquiring new ones.
Outcome: The proposed method outperforms state-of-the-art approaches on ten CNER settings using three datasets.
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) lack robustness in knowledge-intensive tasks due to noisy or irrelevant retrieved data.
Approach: They propose a multi-agent debate-based RAG framework that integrates external knowledge sources into large language models to improve their accuracy.
Outcome: The proposed framework is unsupervised and leverages pretrained LLMs without fine-tuning, making it easily adaptable to various tasks.
The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations.
Approach: They propose a black-box-based framework that captures stubborn hallucinations by integrating internal geometric dynamics with output probability distributions.
Outcome: The proposed framework outperforms white-box methods and reduces computational overhead by over 90%.
Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances, Resources, and Future Directions (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are used to assist with driving decisions, but they face limitations in perception and computational demands.
Approach: They propose a survey of LLM-based multi-agent ADSs and their applications . they analyze agent-human interactions in scenarios where LLM agents engage with humans .
Outcome: The proposed approach reduces human intervention and improves safety and efficiency.
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)

Copied to clipboard

Challenge: Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency.
Approach: They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs.
Outcome: The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks.

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