Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

Flames: Benchmarking Value Alignment of LLMs in Chinese.

[BibT_eX]

[DOI]

Kexin Huang

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

Can AI Assistants Know What They Don't Know?

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Turn Waste into Worth: Rectifying Top-k Router of MoE.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Unified Active Retrieval for Retrieval Augmented Generation.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling.

[BibT_eX]

[DOI]

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

LLM can Achieve Self-Regulation via Hyperparameter Aware Generation.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2024

DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Flames: Benchmarking Value Alignment of Chinese Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Evaluating Hallucinations in Chinese Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Secrets of RLHF in Large Language Models Part I: PPO.

[BibT_eX]

[DOI]

CoRR, 2023

Origin Tracing and Detecting of LLMs.

[BibT_eX]

[DOI]

CoRR, 2023

Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

Improving Contrastive Learning of Sentence Embeddings from AI Feedback.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022

Paradigm Shift in Natural Language Processing.

[BibT_eX]

[DOI]

Int. J. Autom. Comput., 2022

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2022

Multi-Task Pre-Training of Modular Prompt for Few-Shot Learning.

[BibT_eX]

[DOI]

CoRR, 2022

BBTv2: Pure Black-Box Optimization Can Be Comparable to Gradient Descent for Few-Shot Learning.

[BibT_eX]

[DOI]

CoRR, 2022

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

Black-Box Tuning for Language-Model-as-a-Service.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

BBTv2: Towards a Gradient-Free Future with Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022, 2022

2021

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline.

[BibT_eX]

[DOI]

CoRR, 2021

Learning to Teach with Student Feedback.

[BibT_eX]

[DOI]

CoRR, 2021

Early Exiting with Ensemble Internal Classifiers.

[BibT_eX]

[DOI]

CoRR, 2021

Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021

Accelerating BERT Inference for Sequence Labeling via Early-Exit.

[BibT_eX]

[DOI]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

2020

Pre-trained Models for Natural Language Processing: A Survey.

[BibT_eX]

[DOI]

CoRR, 2020

CoLAKE: Contextualized Language and Knowledge Embedding.