Papers by Zhiyuan Zeng

31 papers
FLIQA-AD: a Fusion Model with Large Language Model for Better Diagnose and MMSE Prediction of Alzheimer’s Disease (2025.naacl-short)

Copied to clipboard

Challenge: Existing classification and regression models that only extract finer-grained information from magnetic resonance imaging (MRI) may not be effective for Alzheimer's disease (AD).
Approach: They propose to use a 3D Adapter in a Vision Transformer to extract the patient's EHR information and questions related to the disease as text prompts.
Outcome: The proposed model can discriminate and predict the corresponding MMSE score based on the extracted brain structural information and textual content .
Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System (2021.acl-long)

Copied to clipboard

Challenge: Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set.
Approach: They introduce a task, Novel Slot Detection, in the task-oriented dialogue system.
Outcome: The proposed task is based on two public NSD datasets and proposes strong baselines . it aims to identify a sequence of tokens and extract semantic constituents from user queries .
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning (2022.acl-short)

Copied to clipboard

Challenge: Existing methods to find out out-of-domain (OOD) intents do not take prior knowledge of in-domain data into account.
Approach: They propose a disentangled knowledge transfer method to bridge the gap between IND pre-training and OOD clustering by using a unified multi-head contrastive learning framework.
Outcome: The proposed method is able to group new unknown intents into different clusters, enabling future development of the system.
MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation (2024.acl-long)

Copied to clipboard

Challenge: Existing datasets for event understanding have limited coverage due to complexity of tasks.
Approach: They propose a dataset that augments MAVEN datasets with event argument annotations . they propose 98,591 events and 290,613 arguments obtained with laborious human annotation .
Outcome: The proposed dataset is the first all-in-one dataset supporting event detection, event argument extraction, and event relation extraction.
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter (2021.acl-short)

Copied to clipboard

Challenge: Existing approaches to generating NMT adversarial examples inject perturbations into source sentences or target translations to improve the robustness of NMT models.
Approach: They investigate adversarial attack on NMT from two aspects: languages (the source vs. the target language) and positions (front v. rear).
Outcome: The proposed approach is more effective than adversarial attacks by sampling positions randomly or according to gradients.
Explicit Memory Learning with Expectation Maximization (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models lack reliable learning mechanisms for updating information across interactions.
Approach: They propose a framework that enhances explicit memory updates via the Expectation-Maximization algorithm.
Outcome: The proposed framework outperforms existing methods without memory or with static external memory on streaming inference tasks.
PersLLM: A Personified Training Approach for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves.
Approach: They propose a framework for better data construction and model tuning to unlock the potential of LLM personification by using Chain-of-Thought prompting and anti-induction.
Outcome: The proposed framework improves data construction and model tuning for insufficient data usage and rigid behavior patterns.
UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models (2026.acl-demo)

Copied to clipboard

Challenge: Existing evaluation frameworks for audio foundation models are heavily reliant on English, making it difficult to objectively assess models’ performance on Chinese.
Approach: They propose a unified framework that supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.
Outcome: The proposed framework supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.
KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for retrieval-augmented generation (RAG) are limited and fine-tuning incurs prohibitive costs of external signals.
Approach: They propose a self-supervised framework that enhances RAG systems through efficient model adaptation.
Outcome: The proposed framework achieves 90% of the performance gain obtained through GPT-4-supervised adaptation while relying entirely on self-annotation of much smaller models.
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluation metrics cannot fairly evaluate the outputs of RAG models during training and evaluation.
Approach: They propose a method which prompts LLMs to generate different judgments based on various combinations of judgment dimensions and utilizes the judge-consistency to evaluate these judgments.
Outcome: The proposed method generates more accurate evaluations for RAG models across different RAG model and datasets.
Turn Waste into Worth: Rectifying Top-k Router of MoE (2024.emnlp-main)

Copied to clipboard

Challenge: Top-k router suffers from redundancy computation and memory costs due to unbalanced routing . some experts are overflow, where exceeding tokens are dropped, while others are empty, which are padded with zeros, negatively impacting model performance.
Approach: They propose a top-k router that is unbalanced and uses a multi-gPU system to handle dropped tokens and padding.
Outcome: The proposed model surpasses the top-1 router by 4.7% in terms of performance . the top-k router suffers from redundancy computation and memory costs .
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning (2021.acl-short)

Copied to clipboard

Challenge: Existing methods of OOD detection only focus on whether a sample is correctly classified . lack of real OOD examples leads to poor prior knowledge about these unknown intents .
Approach: They propose a supervised contrastive learning objective to minimize intra-class variance . they employ an adversarial augmentation mechanism to obtain pseudo diverse views .
Outcome: The proposed method minimizes intra-class variance by pulling together in-domain intents belonging to the same class and maximizes inter-class variation by pushing apart samples from different classes.
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? (2025.acl-long)

Copied to clipboard

Challenge: Longer CoTs of o1-like models do not consistently enhance accuracy, causing performance degradation.
Approach: They propose a method that combines parallel scaling strategies with CoT length characteristics to improve models’ test-time scalability.
Outcome: The proposed method improves models’ test-time scalability compared to majority voting approaches.
Emergent Modularity in Pre-trained Transformers (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies on pre-trained Transformers show that they learn fine-grained neuron functions.
Approach: They examine the presence of modularity in pre-trained Transformers . they focus on Mixture-of-Experts, a promising candidate for modularity .
Outcome: The proposed structure stabilizes at the early stage, which is faster than neuron stabilization.
Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance (2024.acl-long)

Copied to clipboard

Challenge: Extensive experiments across various reasoning tasks demonstrate that UAG not only enhances the reasoning abilities of LLMs but consistently outperforms several strong baselines with minimal computational overhead.
Approach: They propose an approach to guide LLMs onto an accurate and reliable trajectory by identifying and adjusting uncertainty signals within each step of the reasoning chain.
Outcome: The proposed approach outperforms strong baselines and outperformed strong models with minimal computational overhead.
BMInf: An Efficient Toolkit for Big Model Inference and Tuning (2022.acl-demo)

Copied to clipboard

Challenge: Recent years, pre-trained language models (PLMs) have achieved promising results on various NLP tasks.
Approach: They propose an open-source toolkit for big model inference and tuning which can support big model tuning at extremely low computation cost.
Outcome: The proposed toolkit can support big model inference and tuning at extremely low computation cost.
Dynamic and Generalizable Process Reward Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing Process Reward Models lack cross-domain generalization and focus on feedback results.
Approach: They propose a process reward model that uses a reward tree to capture and store fine-grained, multi-dimensional reward criteria.
Outcome: The proposed model performs on prevailing benchmarks and out-of-distribution scenarios.
ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit suboptimal behaviors and inconsistencies when exposed to unfamiliar external information, underscoring their limitations in effectively leveraging such knowledge.
Approach: They propose a framework that enhances the external knowledge utilization of Large Language Models through a two-stage constructivist cognitive modeling process.
Outcome: The proposed framework achieves a 10% improvement over baseline methods on various question-answering benchmarks.
Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to optimize LLM for long sequences for long documents are slow and consume memory.
Approach: They propose a method that starts with a small memory size and gradually increases it . they propose Decremental Chunk based on Incremental Memory (IMDC) which reduces chunk size while increasing memory size .
Outcome: The proposed method is faster (1.45x) and reduces GPU memory consumption by 23.3% compared to fixed-size memory.
OpenAttack: An Open-source Textual Adversarial Attack Toolkit (2021.acl-demo)

Copied to clipboard

Challenge: Various attack models are distinct and implemented with different programming frameworks and settings, which hinders quick utilization and fair comparison of attack models.
Approach: They propose an open-source textual adversarial attack toolkit to solve these issues by combining 15 typical attack models into one toolkit.
Outcome: The proposed toolkit supports all attack types, multilinguality, and parallel processing.
LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)

Copied to clipboard

Challenge: E-commerce search relevance is a critical component of retrieval systems.
Approach: They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies.
Outcome: The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain.
Plug-and-Play Knowledge Injection for Pre-trained Language Models (2023.acl-long)

Copied to clipboard

Challenge: Existing knowledge injection methods are not suitable for enhancing pre-trained language models with external knowledge bases.
Approach: They propose a plug-and-play knowledge injection method where knowledge bases are injected into frozen existing downstream models by a knowledge plugin.
Outcome: The proposed method improves the performance of knowledge injection on knowledge-driven tasks while keeping model parameters frozen.
The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation (2023.findings-acl)

Copied to clipboard

Challenge: Event extraction (EE) is a fundamental information extraction task aimed at extracting events from plain texts.
Approach: They propose to specify data preprocessing, standardize outputs, and provide pipeline evaluation results to avoid these pitfalls.
Outcome: The results show that the evaluations are reliable and lack pipeline evaluations.
BMCook: A Task-agnostic Compression Toolkit for Big Models (2022.emnlp-demos)

Copied to clipboard

Challenge: Existing efforts to compress medium-sized models for specific tasks have limited results.
Approach: They propose a task-agnostic compression toolkit for big models that implements quantization, pruning, distillation and MoEfication methods.
Outcome: The proposed tool improves performance on a model with 3 billion parameters by 12x . it also outperforms the original model on three typical NLP benchmarks.
ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation methods for test-time scaling are limited.
Approach: They propose an adaptive resolution-aware scaling evaluation metric specifically designed to assess the test-time scaling effectiveness of large reasoning models.
Outcome: The proposed metric provides a reliable and fine-grained measurement of test-time scaling capabilities, revealing significant variations in scaling efficiency across models.
Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods for OOD detection are based on labeled in-domain data . detecting out-of-domain (OOD) or unknown intents is challenging .
Approach: They propose a novel reassigned contrastive learning method to discriminate IND intents for over-confident OOD and an adaptive class-dependent local threshold mechanism to separate similar IND and OOD intents.
Outcome: The proposed method is effective for both aspects of overconfidence issues.
Adversarial Self-Supervised Learning for Out-of-Domain Detection (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for detecting out-of-domain (OOD) intents are unsupervised and require extensive labeled data.
Approach: They propose a self-supervised contrastive learning framework to model discriminative semantic features from unlabeled data.
Outcome: The proposed framework outperforms baseline methods on two public benchmark datasets with a statistically significant margin.
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization (2021.emnlp-main)

Copied to clipboard

Challenge: Abstractive summarization models often produce inconsistent statements or false facts.
Approach: They propose an efficient weak-supervised adversarial data augmentation approach to generate factual consistency datasets by backpropagating gradients on token embeddings.
Outcome: The proposed model can make interpretable factual errors tracing on public datasets and is cost-effective.
Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for OOD detection are overconfident for OD samples . lack of labeled OOD examples leads to poor prior knowledge about these unknown intents, making it challenging to detect OOD samples.
Approach: They propose a Bayesian OOD detection framework to calibrate distribution uncertainty using Monte-Carlo Dropout.
Outcome: The proposed framework gains 33.33% OOD F1 improvements with increasing only 0.41% inference time compared to previous methods.
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks.
Approach: They propose a hierarchical reasoning aggregation framework to address this problem . they propose dynamic sampling to adjust the number of reasoning chains .
Outcome: The proposed framework outperforms existing ensemble methods on complex reasoning tasks.
ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web (2026.acl-long)

Copied to clipboard

Challenge: Existing routers that use hardcoded tools are limited by scalability and generality bottlenecks.
Approach: They propose a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems.
Outcome: The proposed pipeline can train routers with dynamic context understanding to create the plug-and-play Light Routing Agent.

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