Papers by Kun Bai

10 papers
HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Copied to clipboard

Challenge: Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach: They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome: The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.
Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2 (2021.acl-srw)

Copied to clipboard

Challenge: Experimental results show that pre-trained language model GPT2 can generate better continuations by learning to generate the in the fine-tuning stage.
Approach: They conduct experiments on an English essay dataset using Chinese-GPT2 . they find that the model can generate better continuations by learning to generate the in the fine-tuning stage.
Outcome: The pre-trained language model GPT2 can generate better continuations by learning to generate the in the fine-tuning stage.
Multiplex Word Embeddings for Selectional Preference Acquisition (D19-1)

Copied to clipboard

Challenge: Existing word embeddings are limited in their ability to represent fixed vectors . instead, they incorporate relational dependencies of different words into their embeddables - a limitation that is addressed by a multiplex model .
Approach: They propose a word embedding model which incorporates relational dependencies of different words into their embeddables.
Outcome: The proposed model can be easily extended according to various relations among words.
Joint Coreference Resolution and Character Linking for Multiparty Conversation (2021.eacl-main)

Copied to clipboard

Challenge: Character linking is the task of linking mentioned people in conversations to the real world . human use of pronouns or normal entities makes it difficult to link mentioned people to real people . a critical step towards understanding conversations is grounding mentioned people - a goal of the natural language processing community .
Approach: They propose to integrate richer context from the coreference relations among different mentions to help the linking task.
Outcome: The proposed model outperforms all previous models on both tasks.
Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets (P19-1)

Copied to clipboard

Challenge: Natural Language Sentence Matching (NLSM) is a popular NLP task.
Approach: They propose to use QuoraQP to train and evaluate NLSM models using a selection bias framework.
Outcome: The proposed framework can improve generalization ability of trained models and give more trustworthy evaluation results for real-world adoptions.
Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases (2022.coling-1)

Copied to clipboard

Challenge: Existing methods train one encoder-decoder-based model to fit all questions . however, such a one-size-fits-all strategy may not perform well for complex questions involving multiple KB relations or functional constraints.
Approach: They propose a meta-learning framework for complex question generation over knowledge bases . they propose he meta-trained generator can acquire universal meta-knowledge .
Outcome: The proposed framework can acquire universal and transferable meta-knowledge and quickly adapt to long-tailed samples under different dimensions.
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)

Copied to clipboard

Challenge: Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios.
Approach: They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation .
Outcome: The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead.
Improving Reinforcement Learning Based Image Captioning with Natural Language Prior (D18-1)

Copied to clipboard

Challenge: Recent research shows that Reinforcement Learning (RL) approaches suffer from the exposure bias problem.
Approach: They propose a Reinforcement Learning (RL) based training framework that constrains the action space using an n-gram language prior.
Outcome: The proposed model is more human readable and graceful.
Improving Open-Domain Dialogue Systems via Multi-Turn Incomplete Utterance Restoration (D19-1)

Copied to clipboard

Challenge: Experimental results show that restoring incomplete utterances from context improves the performance of open-domain dialogue systems.
Approach: They propose to use a dataset to restore incomplete utterances from context . they propose to pick and combine the data to restore the incomplete .
Outcome: The proposed model significantly boosts response quality of open-domain dialogue systems.
Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting (2020.acl-main)

Copied to clipboard

Challenge: Recent research has found that text classification datasets contain certain unintended biases, such as text containing demographic identity-terms that are more likely to be abusive.
Approach: They propose a model-agnostic debiasing framework that recovers the non-discrimination distribution using instance weighting, which does not require extra resources or annotations apart from a pre-defined set of demographic identity-terms.
Outcome: The proposed framework alleviates the unintended biases without hurting models’ generalization ability.

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