Papers by Miao Wei

16 papers
Penetrating Linguistic Disguises: A Slang-aware Label-Aligned Framework for Fine-Grained Toxicity Extraction in Chinese Hate Speech Detection (2026.findings-acl)

Copied to clipboard

Challenge: Flexible word boundaries and linguistic obfuscation, particularly slang, challenge precise span-level hate speech detection in Chinese.
Approach: They propose a Slang-aware Label-Aligned Framework that maps slang to explicit hate semantics and uses task-specific branches to mitigate feature interference.
Outcome: The proposed framework reduces ambiguity by mapping obscure slang to explicit hate semantics.
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.
CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)

Copied to clipboard

Challenge: Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences.
Approach: They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks.
Outcome: The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones.
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.
ART: rule bAsed futuRe-inference deducTion (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on language-based premises and deduce valid conclusions from visual observations.
Approach: They propose a rule-based deductive reasoning task that uses video to deduce the correct future event . they use commonsense knowledge to annotate video and a strong baseline to conduct reasoning .
Outcome: Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations . ART is a method that rigorously follows a set of explicit constraints to deduce valid conclusions from empirical facts .
SAM3-I: Segment Anything with Instructions (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering.
Approach: They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework.
Outcome: Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability.
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach: They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome: Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.
Qwen2.5-xCoder: Multi-Agent Collaboration for Multilingual Code Instruction Tuning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to train code LLMs view each programming language in isolation . experimental results show that Qwen2.5-xCoder can bridge the gap between different programming languages .
Approach: They propose a framework that allows agents to collaborate to enhance multilingual instruction tuning for code LLMs.
Outcome: Experimental results show that Qwen2.5-xCoder can transfer knowledge efficiently and effectively between languages.
MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses (2025.emnlp-main)

Copied to clipboard

Challenge: Existing medical fact-checking datasets focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored.
Approach: They propose to use Chinese medical fact-checking datasets to verify LLM-generated medical content by combining in-context learning and fine-tuning.
Outcome: The first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content consists of 1,321 questions and 7,409 claims .
Towards Protecting Vital Healthcare Programs by Extracting Actionable Knowledge from Policy (2021.findings-acl)

Copied to clipboard

Challenge: In the U.S., an estimated annual amount of USD$20-30B is lost to Fraud, Waste and abuse (FWA)
Approach: They propose a method for automatically extracting knowledge from healthcare policy documents into a semantically-meaningful knowledge graph of rules.
Outcome: The proposed method fuses advances in dependency parsing with a policy ontology to transform the content of regulatory healthcare policy into human-friendly policy rules with human oversight.
The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing multilingual evaluation benchmarks neglect cultural nuances and lack language coverage in subjective tasks.
Approach: They propose a framework that categorizes evaluation tasks into three cultural layers and nine cognitive sub-layers.
Outcome: The proposed framework surpasses prior coverage by up to 111% on 20+ LLMs.
Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)

Copied to clipboard

Challenge: Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal.
Approach: They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs.
Outcome: The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs.
A Survey of Link Prediction in N-ary Knowledge Graphs (2025.emnlp-main)

Copied to clipboard

Challenge: N-ary Knowledge Graphs (NKGs) capture n-ary facts containing more than two entities.
Approach: They present the first comprehensive survey of link prediction in NKGs . they provide an overview of the field and analyze their performance and application scenarios .
Outcome: The proposed methods provide an overview of the field and analyze performance and application scenarios.
SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters (2026.acl-long)

Copied to clipboard

Challenge: Prompt-based in-context learning and parameter fine-tuning are dominant paradigms for incorporating external information into large language models, but they incur high inference costs or require expensive retraining.
Approach: They propose to convert prompts into temporary adapter weights to bridge this gap by converting prompts to temporary adapters.
Outcome: The proposed model outperforms baselines on long-context language modeling and downstream NLU and summarization benchmarks while significantly reducing memory footprint and latency.

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