101 citations
- Peking UniversityCN113 papers
- Chinese Academy of SciencesCN25 papers
- University of Chinese Academy of SciencesCN18 papers
- National Astronomical ObservatoriesCN15 papers
- Astronomy and SpaceAU12 papers
- Shanghai Jiao Tong UniversityCN12 papers
- Centre National de la Recherche ScientifiqueFR11 papers
- Collaborative Innovation Center of Quantum MatterCN11 papers
- University of ChicagoUS10 papers
- Sorbonne UniversitéFR9 papers
- The University of TokyoJP9 papers
- University of ArizonaUS9 papers
9 papers · 1 filter
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives
Junyu Luo, Bohan Wu, Xiao Luo +8
Post-training of Large Language Models (LLMs) is crucial for unlocking their task generalization potential and domain-specific capabilities. However, the current LLM post-training…
Unlocking the Potential of Model Merging for Low-Resource Languages
Mingxu Tao, Chen Zhang, Quzhe Huang +4
Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach s…
Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
Zhe Lin, Xiaojun Wan
In recent years, neural paraphrase generation based on Seq2Seq has achieved superior performance, however, the generated paraphrase still has the problem of lack of diversity. In t…
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
Pan Lu, Ran Gong, Shibiao Jiang +4
Geometry problem solving has attracted much attention in the NLP community recently. The task is challenging as it requires abstract problem understanding and symbolic reasoning wi…
Lattice CNNs for Matching Based Chinese Question Answering
Yuxuan Lai, Yansong Feng, Xiaohan Yu +3
Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages lik…
Sentence-wise Smooth Regularization for Sequence to Sequence Learning
Chengyue Gong, Xu Tan, Di He +1
Maximum-likelihood estimation (MLE) is widely used in sequence to sequence tasks for model training. It uniformly treats the generation/prediction of each target token as multi-cla…