Papers by Junfeng Yao

10 papers
A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Version updates are an indispensable requirement for Large Language Models . a large learning rate in the first stage and a complete learning decay process are crucial for version updates of LLMs.
Approach: They propose a learning rate path switching training paradigm for version updates of Large Language Models.
Outcome: The proposed paradigm reduces training cost to 58% when training four versions of LLMs compared to PTFS and CPT .
Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies on relation extraction ignore non-bridge entities, leading to bias during inference.
Approach: They propose a graph-based cross-document Relation Extraction model with non-bridge entity enhancement and prediction debiasing that integrates non-cross entities with target entities and bridge entities.
Outcome: The proposed model outperforms baseline models on open and closed datasets.
Benchmarking and Learning Real-World Customer Service Dialogue (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) focus on task completion and tool correctness.
Approach: They propose a benchmark-to-optimization loop that bridges offline gains to deployment . they propose OlaMind, which distills reusable reasoning patterns from expert dialogues .
Outcome: The proposed benchmark surpasses GPT-5.2 and Gemini 3 Pro on OlaBench . it delivers an average +23.67% issue resolution and -6.6% human transfer rate versus baseline .
Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to train LLMs on previous training data are not feasible in real-world applications because of catastrophic forgetting.
Approach: They propose a framework that uses the LLM to generate synthetic instances for rehearsal and refine the instance outputs based on the synthetic inputs.
Outcome: The proposed framework achieves superior or comparable performance compared to conventional rehearsal-based approaches while being more data-efficient.
AGCL: Aspect Graph Construction and Learning for Aspect-level Sentiment Classification (2025.coling-main)

Copied to clipboard

Challenge: Aspect-level Sentiment Classification (ALSC) is a fine-grained sentiment analysis task that aims to identify the sentiment polarity of a review text toward each corresponding aspect.
Approach: They propose a novel Aspect Graph Construction and Learning method that harnesses aspect connections to construct a domain aspect graph and iteratively updates it to enhance its domain expertise.
Outcome: The proposed method can bridge unseen aspects with seen aspects, enhancing the model's generalization capability.
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to address hallucinations in large vision-language models require substantial computational cost and time.
Approach: They propose to leverage sparse autoencoders to identify semantic directions closely associated with faithfulness or hallucination, extracting more precise and disentangled hallucinian-related representations.
Outcome: The proposed method outperforms existing decoding approaches while maintaining transferability across different model architectures with negligible additional time overhead.
Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings (2021.emnlp-main)

Copied to clipboard

Challenge: Existing sentence ordering models can be classified into pairwise ordering models and set-to-sequence models.
Approach: They propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering.
Outcome: The proposed model achieves state-of-the-art performance on five commonly-used datasets.
EmoTrans: Emotional Transition-based Model for Emotion Recognition in Conversation (2024.lrec-main)

Copied to clipboard

Challenge: Emotions are causally transmitted among communication participants, facilitating comprehension of intricate changes in emotional states during the conversation.
Approach: They propose an Emotional Transition-based Emotion Recognizer that captures ET features in an emotional conversation by concatenating the most recent utterances with their corresponding speakers.
Outcome: The proposed model is sensitive to emotions and captures ET features in the sample.
Revisiting Non-Autoregressive Translation at Scale (2023.findings-acl)

Copied to clipboard

Challenge: Extensive experiments on two advanced NAT models show scaling can improve translation performance.
Approach: They empirically examine the impact of scaling on NAT behaviors on a large-scale WMT dataset.
Outcome: The proposed model can achieve comparable performance with the scaling model while maintaining the superiority of decoding speed with standard NAT models.
Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for terminology translation struggle with interference from irrelevant noise.
Approach: They propose a Locate-and-Focus method that locates terminologies within utterances to construct translation knowledge by minimizing irrelevant information for ST models.
Outcome: The proposed method locates terminologies within utterances and enhances the success rate of terminology translation while maintaining robust general translation performance.

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