Papers by Zhen Tan

33 papers
Semantic and Sentiment Dual-Enhanced Generative Model for Script Event Prediction (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to model event associations struggle with semantic ambiguity and embedding bias.
Approach: They propose a Semantic and Sentiment Dual-enhanced Generative Model to address these issues . it leverages two types of script event information to enhance the generative model .
Outcome: The proposed model captures both global and local sentiments of events through its sentiment awareness mechanism.
Dynamic-prototype Contrastive Fine-tuning for Continual Few-shot Relation Extraction with Unseen Relation Detection (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to learn relations from labeled data overlook task interference in continual learning and memory requirements for different relations.
Approach: They propose a framework to learn new relations from limited labeled data while preserving knowledge about previously learned relations.
Outcome: The proposed framework is more practical and comprehensive for real-world scenarios.
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.
SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention (2025.acl-long)

Copied to clipboard

Challenge: Content analysis is labor-intensive and time-consuming process that requires multiple rounds of manual annotation, domain expert discussion, and rule-based refinement.
Approach: They propose a multi-agent framework that effectively Simulates Content Analysis via Large language model (LLM) ag Ents.
Outcome: The proposed framework achieves human-approximated performance across various content analysis tasks.
DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large language models have achieved promising performances across various applications, but the challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains.
Approach: They propose a dynamic co-augmentation framework for the refinement of large language models and knowledge graphs in the context of Alzheimer's Disease.
Outcome: The proposed framework can be used to study Alzheimer's Disease (AD) using LLMs and KGs.
Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors.
Approach: They propose a metacognitive framework that enables step-level error detection and self-correction in Large Language Model based multi-agent systems (MAS) .
Outcome: The proposed framework outperforms baselines on the Who When benchmark and delivers consistent gains on AgentErrorBench.
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations.
Approach: They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval.
Outcome: The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model.
CLEEK: A Chinese Long-text Corpus for Entity Linking (2020.lrec-1)

Copied to clipboard

Challenge: Entity linking is a fundamental task in natural language processing, says nigel kilgstrom . existing corpora for entity linking in china are lacking and deficient, he says . kilsmstrom: a new method for entity disambiguation can be developed for Chinese .
Approach: They build a Chinese corpus of multi-domain long text for entity linking . they evaluate the difficulty of documents with respect to entity linking using a measure .
Outcome: The proposed corpus is based on 100 documents from diverse domains and is publicly accessible.
EQA-RM: A Generative Embodied Reward Model with Test-time Scaling (2025.emnlp-main)

Copied to clipboard

Challenge: Existing generic Reward Models are ill-equipped for dynamic and interactive domains.
Approach: They propose a novel generative multimodal reward model specifically architected for EQA that provides interpretable, structured reward feedback.
Outcome: The proposed model outperforms proprietary benchmarks, including Gemini-2.5-Flash, GPT-4o, Claude-3.5-Haiku, and open-sourced state-of-the-art models such as RoVRM and VisualPRM.
Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance (2023.findings-emnlp)

Copied to clipboard

Challenge: Pretrained Language Models (PLMs) are advanced but data labels are noisy due to the complex annotation process.
Approach: They propose a framework for fine-tuning PLMs using noisy labels that incorporates guidance from Large Language Models like ChatGPT.
Outcome: Experiments on synthetic and real-world noisy datasets show that the proposed framework outperforms the state-of-the-art framework.
ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents (2026.findings-acl)

Copied to clipboard

Challenge: Reward-guided search methods have shown potential in enhancing tool-using agents . however, there is a lack of reliable evaluation benchmarks for PRMs in tool-use settings .
Approach: They propose a large-scale benchmark specifically designed to evaluate PRMs for tool-using agents.
Outcome: The proposed benchmark shows that tool reward models perform better in tool-using environments.
Active Learning for Abstractive Text Summarization via LLM-Determined Curriculum and Certainty Gain Maximization (2024.findings-emnlp)

Copied to clipboard

Challenge: Abstractive text summarization (ATS) requires laborious data annotation and time-consuming model training.
Approach: They propose a novel active learning framework that asks large language models to rate difficulty of instances and then uses certainty gain maximization to select instances with a distribution that aligns well with the overall distribution.
Outcome: The proposed framework improves stability, effectiveness, and efficiency of abstractive text summarization backbones.
Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to detect causal relationships in unstructured texts ignore trivial knowledge which may prejudice performance.
Approach: They propose a pipeline to build a commonsense-aware pre-trained model which integrates reliable task-specific knowledge from commonsens graphs.
Outcome: The proposed pipeline integrates reliable task-specific knowledge from commonsense graphs.
TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)

Copied to clipboard

Challenge: Prior work has focused on treating subwords as basic units in developing such systems.
Approach: They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences.
Outcome: The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks.
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2026.findings-acl)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning from large language models (LLMs).
Approach: They propose a data distribution lens to understand when and why CoT reasoning fails . they propose 'data-based' training that trains LLMs from scratch .
Outcome: The proposed model enables models to generate reasoning trajectories that approximate those observed during training.
Task-Aware Resolution Optimization for Visual Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing visual large language models pre-assume a fixed resolution for downstream tasks, leading to sub-optimal performance.
Approach: They propose a formula to determine the optimal resolution for a given vision-language task . they then propose 'parameter-efficient' fine-tuning technique to extend the visual input resolution .
Outcome: The proposed method is based on rigorous experiments on vision-language tasks.
Contextualization Distillation from Large Language Model for Knowledge Graph Completion (2024.findings-eacl)

Copied to clipboard

Challenge: Existing knowledge graph completion models lack textual information, which limits their performance . a plug-in-and-play approach is needed to train small models in descriptive context .
Approach: They propose a plug-in-and-play approach to knowledge graph completion that prompts LLMs to generate descriptive context.
Outcome: The proposed method improves performance on Wikipedia articles and synset definitions.
Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data.
Approach: They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students.
Outcome: Experiments show that QR-Distill is superior to traditional methods.
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios .
Approach: They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios.
Outcome: The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm.
Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) demonstrate exceptional instruct-following ability to complete downstream tasks.
Approach: They propose a black-box combinatorial optimization framework that iteratively improves lexical choices in prompts by a search strategy related to word influence.
Outcome: The proposed framework recovers the model's ability to instruct-follow and solve downstream tasks even when the variations are imperceptible to humans.
Glue pizza and eat rocks - Exploiting Vulnerabilities in Retrieval-Augmented Generative Models (2024.emnlp-main)

Copied to clipboard

Challenge: Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases.
Approach: They propose to exploit openness of RAG models by injecting deceptive content into the retrieval database, intentionally changing the model’s behavior.
Outcome: The proposed model can be exploited through crafted content uploads with access to the retriever.
Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks (2025.acl-long)

Copied to clipboard

Challenge: Multi-agent LLMs are prone to adversarial attacks because of constraints such as limited token bandwidth and latency between message delivery.
Approach: They propose a permutation-invariant adversarial attack that optimizes prompt distribution across latency and bandwidth constraints to bypass distributed safety mechanisms within the system.
Outcome: The proposed method outperforms conventional attacks by up to 7 on multiple models.
PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to generate long music are inefficient and lack of structured representation.
Approach: They propose a hierarchical discrete representation of audio for long audio-domain music generation using residual vector quantization on different levels of features.
Outcome: The proposed method achieves competitive performance in terms of reconstruction quality and token per second (TPS) the proposed method facilitates training a language model that can generate well-structured long-form music for up to 3 minutes.
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates (2023.tacl-1)

Copied to clipboard

Challenge: Named Entity Recognition (NER) has evolved from flat to overlapped and discontinuous . NER is a text recognition task that recognizes mentions that represent entities in text .
Approach: They propose a two-stage span-based framework to solve a unified NER task using two stages . they extract entity spans, classify over all entity span pairs and combine them to train two stages.
Outcome: The proposed framework beats all the current competitive baselines on eight benchmark datasets, obtaining the best performance of unified NER.
AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for multi-agent collaboration rely on static or graph-based topologies lacking flexibility and adaptability.
Approach: They propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.
Outcome: The proposed method achieves superior performance while significantly reducing communication overhead.
Joint Event Extraction with Hierarchical Policy Network (2020.coling-main)

Copied to clipboard

Challenge: Existing work on event extraction (EE) is pipelined or uses a joint structure but does not utilize information interactions among event triggers, event arguments, and argument roles.
Approach: They propose to exploit role information of arguments in an event and devise a Hierarchical Policy Network to perform joint EE.
Outcome: The proposed system outperforms existing methods and is more powerful for sentences with multiple events.
Curriculum Learning based Hierarchical Scoring and Analysis Framework for Question Answering Task Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation methods rely on rule-based matching with shallow semantic understanding or adopt LLM-as-a-Judge approaches that incur high cost and latency while offering limited error interpretability.
Approach: They propose a curriculum learning based hierarchical framework for QA task evaluation that supports quick scoring and fine-grained error analysis.
Outcome: The proposed framework outperforms baseline methods on quick scoring and error analysis tasks while being 25 faster.
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach: They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome: The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.
Large Language Models for Data Annotation and Synthesis: A Survey (2024.emnlp-main)

Copied to clipboard

Challenge: Existing surveys focus on LLMs' specific utility for data annotation and synthesis.
Approach: They propose to use large language models to generate annotations from raw data . they also propose to review learning strategies for models utilizing LLM-generated annotations .
Outcome: The proposed models can be used to improve the efficacy of machine learning models by generating and labeling raw data with relevant information.
UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets (2025.emnlp-main)

Copied to clipboard

Challenge: Existing datasets address understanding and generation in isolation, limiting the performance of unified vision large language models.
Approach: They propose a dataset that facilitates mutual enhancement between multimodal understanding and generation.
Outcome: The proposed framework integrates diverse visual and textual inputs and outputs, enabling comprehensive cross-modal reasoning and precise text-to-image alignment.
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Copied to clipboard

Challenge: a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach: They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome: The proposed benchmarks show that the current models perform worse than the human ceiling.
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 Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been focused on single-agent, white-box environments, but multi-agend systems (MAS) have a critical blind spot: supply chain vulnerabilities.
Approach: They propose a black-box auditing framework that leverages an Evolutionary Algorithm to autonomously expose hidden threats.
Outcome: The proposed framework achieves superior detection rates (up to 100% in specific configurations) and robustness across diverse architectures.

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