Papers by Miao Yu

18 papers
Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing defenses rely on impractical assumptions about trigger settings to mitigate backdoor attacks . a recent study found that small amounts of training data can systematically induce harmful behaviors in large language models.
Approach: They propose a backdoor defense framework that requires no prior knowledge of trigger settings . they use a two-stage process to aggregate backdoor representations and fine-tune recovery .
Outcome: The proposed defense reduces the average Attack Success Rate to 4.41% across multiple benchmarks . the proposed framework generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.
ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)

Copied to clipboard

Challenge: ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge.
Approach: They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks .
Outcome: ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering.
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection (2021.naacl-main)

Copied to clipboard

Challenge: Existing datasets for sarcasm detection are limited due to the difficulty in acquiring ground-truth annotations.
Approach: They propose a generalized latent optimization strategy that allows different losses to accommodate each other and improves training dynamics.
Outcome: The proposed approach outperforms transfer learning and meta-learning baselines and achieves 10.02% performance gain on the iSarcasm dataset.
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning (2024.acl-long)

Copied to clipboard

Challenge: Recent research shows that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information.
Approach: They propose to use contrastive learning to promote global feature alignment and learning counterfactual clues to improve model performance.
Outcome: The proposed method outperforms the state-of-the-art on out-of distribution (OOD) datasets.
LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents.
Approach: They propose to integrate human-provided information, feedback, or control into the agent system to enhance system performance, reliability, and safety.
Outcome: The proposed systems improve system performance, reliability, and safety by integrating human-provided information, feedback, or control into the agent system.
SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for document-level relation extraction ignore bidirectional mention interaction when generating relational features for entity pairs.
Approach: They propose a document-level relation extraction model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module for relation prediction.
Outcome: The proposed model achieves SOTA performance and the proposed method is effective and general when integrated into existing models.
DocumentNet: Bridging the Data Gap in Document Pre-training (2023.emnlp-industry)

Copied to clipboard

Challenge: Document understanding tasks are a tedious task that requires extensive training and privacy constraints.
Approach: They propose a method to collect weakly labeled data from the web to benefit VDER training . the collected dataset does not depend on specific document types or entity sets .
Outcome: The proposed method does not depend on specific document types or entity sets, making it universally applicable to all VDER tasks.
AgentAsk: Multi-Agent Systems Need to Ask (2026.acl-long)

Copied to clipboard

Challenge: Multi-agent systems fail to consistently outperform strong single-a agent baselines due to error propagation at inter-aggent message handoffs.
Approach: They propose an edge-level error taxonomy that identifies four main errors in multi-agent interactions as data gaps, signal corruption, referential drift and capacity gaps as primary sources of failure.
Outcome: The proposed module outperforms existing systems on five benchmarks and is architecture-agnostic.
MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation benchmarks for LLM unit test generation focus on function-level code rather than on more practical, challenging multi-file codebases.
Approach: They propose a multi-file-level benchmark for unit test generation covering Python, Java, and JavaScript.
Outcome: The proposed benchmarks show that most LLMs exhibit moderate performance on MultiFileTest, highlighting the benchmark’s inherent difficulty.
SPM: A Split-Parsing Method for Joint Multi-Intent Detection and Slot Filling (2023.acl-industry)

Copied to clipboard

Challenge: Existing studies focus on utterances with a single intent, but lack the ability to assign slots to each corresponding intent.
Approach: They propose a split-parsing method for joint intent detection and slot filling . they split an input sentence into multiple sub-sentences which contain a single-intent .
Outcome: The proposed method improves on three multi-intent datasets on multi-tasks.
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Copied to clipboard

Challenge: Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach: AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome: Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .
G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems (2025.acl-long)

Copied to clipboard

Challenge: Large Language Model (LLM)-based Multi-agent Systems (MAS) have demonstrated remarkable capabilities in various complex tasks, but their vulnerability to adversarial attacks, misinformation propagation, and unintended behaviors have raised significant concerns.
Approach: They propose a topology-guided security lens and treatment for robust LLM-MAS that leverages graph neural networks to detect anomalies on the multi-agent utterance graph and employ topological intervention for attack remediation.
Outcome: Experiments show that the proposed security lens recovers 40% of the performance under various attack strategies and integrates with mainstream MAS with security guarantees.
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to retrieval augmented generation neglect PDF structure and layout . individual PDFs often exceed prompt limits and user queries may span multiple documents.
Approach: They propose a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process.
Outcome: The proposed framework organizes semi-structured PDF content into relational database and vectorstore . it defeats both RAG and structured baselines on three PDF-based QA datasets .
NetSafe: Exploring the Topological Safety of Multi-agent System (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have fueled significant progress in intelligent Multi-agent Systems (MAS), with expanding academic and industrial applications.
Approach: They propose a framework that unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.
Outcome: The proposed framework unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.
MoE-I2: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition (2024.findings-emnlp)

Copied to clipboard

Challenge: emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models.
Approach: They propose a two-stage compression method tailored for Mixture of Experts to reduce the model size and decrease the computational cost.
Outcome: The proposed method reduces model size and improves inference efficiency while maintaining performance in various zero-shot tasks.
Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing graph anomaly detection methods rely on coarse sentence-level information and overlook fine-grained lexical cues, limiting their reliability and real-world applicability.
Approach: They propose an explainable and fine-grained safeguarding framework for detecting malicious agents in multi-agent systems (MAS) to incorporate both coarse and fine lexical information for anomalous agent identification.
Outcome: Extensive experiments across diverse MAS topologies and attack scenarios demonstrate robust detection performance and strong interpretability of XG-Guard.
Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning (2025.findings-acl)

Copied to clipboard

Challenge: Long-CoT reasoning and reinforcement learning are demonstrating remarkable performance and scalability, however, there is a lack of systematic guidelines for obtaining a better initial policy model.
Approach: They propose a systematic guideline and a novel Re-RFT method to obtain more efficient reasoning patterns from different initial models.
Outcome: The proposed method surpasses DeepSeek-R1-Distill-Qwen-14B model by 4.6%, demonstrating its effectiveness and superiority.
Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety (2026.acl-long)

Copied to clipboard

Challenge: Existing deep research frameworks lack adequate evaluation procedures and stage-specific protections.
Approach: They propose a framework with open-domain evaluation and a stage-wise safety benchmark to address this oversight.
Outcome: The proposed framework improves defense success rates by 16.53% while reducing over-refusal rates to approximately 6%.

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