Papers by Aimin Yang

11 papers
Are U a Joke Master? Pun Generation via Multi-Stage Curriculum Learning towards a Humor LLM (2024.findings-acl)

Copied to clipboard

Challenge: Existing research has demonstrated that the ability of large language models (LLMs) to generate humorous sentences is limited to producing 25 unique jokes.
Approach: They propose a multi-stage curriculum preference learning framework to optimize both pun structure preferences and humor preferences by a Chinese Pun dataset.
Outcome: The proposed method significantly outperforms baseline models on Chinese and English benchmark datasets.
The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights (2025.acl-long)

Copied to clipboard

Challenge: Existing models that leverage visual information do not improve math reasoning performance . authors suggest that visual information is important for multimodal reasoning .
Approach: They propose a dataset to require image reliance for problem-solving and challenge models with similar, yet distinct, images that change the correct answer.
Outcome: The proposed model performance is unaffected by changes to or removal of images in the dataset.
SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation (2026.findings-acl)

Copied to clipboard

Challenge: Text-to-Video (T2V) generation is a challenge under complex scenarios.
Approach: They propose a scenario-aware and self-correcting multi-agent prompt refinement framework for T2V prompting.
Outcome: The proposed framework improves text-to-video alignment and overall generation quality under complex scenarios.
An Effective Deployment of Contrastive Learning in Multi-label Text Classification (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies on contrastive learning in natural language processing tasks have not explored the effectiveness of the technology.
Approach: They propose five novel contrastive losses for multi-label text classification tasks that exploit the complexity of the input logic and the semantic representation space.
Outcome: The proposed contrastive losses improve multi-label text classification tasks and can be adapted for multi-task tasks.
Jailbreaking? One Step Is Enough! (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs.
Approach: They propose a Reverse Embedded Defense Attack mechanism that disguises the attack intention as the "defense" intention against harmful content.
Outcome: The proposed method outperforms existing methods on open-source and closed-source models and enables successful jailbreak in one iteration.
IndoCL: Benchmarking Indonesian Language Development Assessment (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent interest has surged in applying natural language processing (NLP) and machine learning (ML) to evaluate language development in both first (L1) and second (L2) language acquisition.
Approach: They propose to use an Indonesian corpus as a benchmark for LDA tasks and to use existing large-scale language models to improve performance.
Outcome: The proposed model extracts language-independent features, relieving laborious computation and reliance on specific language.
Deputy: Accelerating Large Language Model Inference with Dynamic Low-Rank Substitution (2026.findings-acl)

Copied to clipboard

Challenge: Existing dynamic schemes such as early-exit and layer-drop reduce FLOPs but break batch processing or introduce KV-cache inconsistency.
Approach: They propose a dynamic low-rank substitution framework that employs a lightweight decision module at each layer to dynamically determine the execution branch for different tokens.
Outcome: The proposed model reduces computation by approximately 40% compared to the original dense model while outperforming existing baseline methods.
FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, but their proficiency and reliability in the specialized domain of financial data analysis remain uncertain.
Approach: FinDABench is a benchmark designed to evaluate the financial data analysis capabilities of Large Language Models (LLMs) it comprises 15,200 training instances and 8,900 test instances, all meticulously crafted by human experts.
Outcome: FinDABench measures the financial data analysis capabilities of large language models (LLMs) across three dimensions: 1) Core Ability; 2) Analytical Ability; 3) Technical Ability.
FlattenQuant: Breaking through the Inference Compute-bound for Large Language Models with Per-tensor Quantization (2024.lrec-main)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated state-of-the-art accuracies across tasks, but their latency and GPU memory consumption limit their performance.
Approach: They propose a method which flattens the tensor to achieve low bit per-tensori quantization with minimal accuracy loss.
Outcome: The proposed method achieves low bit per-tensor quantization with minimal accuracy loss.
Rethinking Vocabulary Augmentation: Addressing the Challenges of Low-Resource Languages in Multilingual Models (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to augment vocabularies ignore the disparities between model representation and frequency distributions.
Approach: They propose an Entropy-Consistency Word Selection method which integrates semantic and frequency metrics for vocabulary augmentation.
Outcome: The proposed method improves performance for low-resource languages compared to high-resourced ones . it integrates semantic and frequency metrics for vocabulary augmentation .
Pseudo-label Data Construction Method and Syntax-enhanced Model for Chinese Semantic Error Recognition (2025.coling-main)

Copied to clipboard

Challenge: Existing research on Chinese text error recognition has focused on pre-trained models, but training them from scratch is time-consuming and laborious.
Approach: They propose a method for Chinese Semantic Error Recognition that generates pseudo-labels for augmented samples based on perplexity and model respectively.
Outcome: The proposed method surpasses existing models in Chinese text error recognition due to Chinese semantics' complexity.

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