Papers by Ao Yang

14 papers
Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training (2025.naacl-long)

Copied to clipboard

Challenge: Current PP methods face severe bottlenecks, including pipeline bubbles and memory footprint.
Approach: They propose a sequence-level one-forward-one-backward (1F1B) PP method for training LLMs on long sequences with high throughput and memory efficiency.
Outcome: The proposed method achieves 1.14X training throughput with half memory footprint compared to baseline methods . it trains an LLM with 30B parameters on sequences up to 64k tokens using 64X NVIDIA A100 GPUs .
A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis (D19-1)

Copied to clipboard

Challenge: Existing ABSA methods only use one aspect or multiple aspects with the same sentiment polarity . recent studies show that neural network methods can be trained end-to-end and automatically learn important features.
Approach: They propose a large-scale multi-aspect multi-sentiment dataset with two different aspects with different sentiment polarities.
Outcome: The proposed model outperforms the state-of-the-art models on the large-scale dataset . it is based on a novel neural network approach that can be trained end-to-end .
ToolCPT: Improving Tool Utilization in LLM Agents via Continuous Pre-training (2026.findings-acl)

Copied to clipboard

Challenge: Current approaches to enhancing tool use for LLM-based agents focus on post-training fine-tuning or test-time context extension.
Approach: They propose to enhance tool knowledge for LLM-based agents during continuous pre-training . they curate 5.1 million code artifacts from large-scale, high-quality code repositories .
Outcome: The proposed model outperforms existing methods on out-of-distribution tools on multiple benchmarks.
Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance (2026.acl-long)

Copied to clipboard

Challenge: Existing token-level attacks have shown efficacy on open-source models but suffer from poor cross-model transferability.
Approach: They propose a framework to improve cross-model transferability by modifying model parameters and generating update directions according to differences in output distributions rather than parameter-space distances.
Outcome: The proposed framework improves cross-model transferability and success rates on open-source models.
Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks (2024.emnlp-main)

Copied to clipboard

Challenge: Existing text attack methods are designed for English text, but robust implementation of Chinese text is understudied.
Approach: They propose an adaptive immune-based sound-shape code algorithm for Chinese text attacks . they leverage the Sound-Shape Code to generate natural substitutions .
Outcome: The proposed algorithm produces high-quality Chinese adversarial examples . it can reduce duplication of population and improve search ability .
Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to image paragraph captioning ignore the past alignment information, resulting in repetitive captioning and incomplete captioning.
Approach: They propose an Interactive key-value Memory-augmented Attention model for image paragraph captioning to keep track of attention history along with update-chain of decoder state.
Outcome: Extensive experiments on a benchmark dataset demonstrate the effectiveness of the proposed model.
Reading Like HER: Human Reading Inspired Extractive Summarization (D19-1)

Copied to clipboard

Challenge: Existing methods for extracting text summarization are abstractive and extractive.
Approach: They propose a novel approach for extractive summarization by simulating two stages . they adopt a convolutional neural network to encode gist of paragraphs for rough reading .
Outcome: The proposed method significantly outperforms the state-of-the-art extractive methods on CNN and DailyMail datasets.
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance.
Approach: They propose a method that reweights rewards by a factor approximately proportional to Evidence Gain and assigns higher weights to high-quality traces without requiring costly computation.
Outcome: Experiments on mathematical reasoning benchmarks show that Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally.
E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: despite the rapid development of Large Language Models, there is no dedicated benchmark for evaluating LLMs in Chinese K-12 education.
Approach: They propose to develop a benchmark specifically tailored for Chinese K-12 education.
Outcome: EVAL is the first evaluation benchmark specifically tailored for Chinese K-12 education.
Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies aim to integrate multiple sub-tasks into a unified ABSA model but suffer from major disadvantages .
Approach: They propose a multi-task learning approach to make use of sub-tasks for a unified ABSA.
Outcome: The proposed model can work well when some sub-tasks are absent, and the interactive relations among subtasks not adequate.
Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph (2020.coling-main)

Copied to clipboard

Challenge: Existing studies rely on deep graph neural networks (GNNs) to capture rich structural information, but they lack the structural information needed for QA.
Approach: They propose a framework which captures structural information from KBs and models long-distance node relations from two perspectives.
Outcome: The proposed framework models long-distance node relations from two perspectives . it is based on two widely used multi-hop KBQA datasets .
Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for estimating attention importance for tokens are ineffective . dLLMs require bidirectional attention, which limits inference efficiency .
Approach: They propose a training-free attention sparsification framework for efficient long-context inference . they propose 'sink-aware pruning strategy' to accurately estimate and remove redundant computation .
Outcome: The proposed approach offers 29 lossless speedup under 32K context length.
Quantification of Large Language Model Distillation (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have revealed the robustness degra-dation caused by data distillation.
Approach: They propose a framework to evaluate and quantify model distillation . they aim to identify identity cognition contradictions and analyse multi-granularity response similarities across models to measure the extent of homogenization.
Outcome: The proposed framework addresses two key aspects: (1) Identifying identity cognition contradictions to assess discrepancies in how models perceive and represent identity-related information; (2) Analyzing multi-granularity response similarities across models to measure the extent of homogenization.
AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to improve embeddings from Mixture-of-Experts models allocate a fixed number of experts uniformly across all layers and tokens, ignoring inter-layer and inter-token heterogeneity.
Approach: They propose an Adaptive Expert Allocation framework that performs layer-wise and token-wise expert allocation to enhance embedding quality.
Outcome: The proposed method improves embedding quality across multiple MoE models.

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