Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Latte: Transfering LLMs' Latent-level Knowledge for Few-shot Tabular Learning
Authors: Ruxue Shi, Hengrui Gu, Hangting Ye, Yiwei Dai, Xu Shen, Xin Wang
IJCAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on various few-shot tabular learning benchmarks demonstrate the superior performance of Latte, establishing it as a state-of-the-art approach in this domain. Our code is available at https://github.com/ruxueshi/Latte.git. We conducted extensive experiments to validate Latte s effectiveness on few-shot tabular learning tasks. Latte consistently outperforms all competing methods by a significant margin across various datasets and prediction tasks. Comprehensive ablation studies further highlight the superiority of latent-level knowledge over text-level knowledge, as well as the effectiveness of the individual components in this framework. |
| Researcher Affiliation | Academia | Ruxue Shi , Hengrui Gu , Hangting Ye , Yiwei Dai , Xu Shen and Xin Wang Jilin University, Changchun, China EMAIL, EMAIL |
| Pseudocode | No | The paper describes the methodology in natural language and mathematical equations but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/ruxueshi/Latte.git. |
| Open Datasets | Yes | As shown in Table 1, we evaluate the proposed method using nine real-world datasets, including six classification tasks and three regression tasks. Each dataset provides metadata such as a clear description for each attribute and task. Refer to Appendix A for details of the dataset Baselines. |
| Dataset Splits | No | The paper defines few-shot learning scenarios using 'N-way K-shot meta-training tasks' where 'k' labeled samples are selected per class (with k varying as 4, 8, 16, 32, 64 shots as shown in Table 2). However, it does not provide explicit percentages or absolute counts for the overall training, validation, and test splits for the entire datasets. |
| Hardware Specification | No | The paper discusses model architectures and training parameters but does not provide any specific hardware details such as GPU or CPU models used for running the experiments. |
| Software Dependencies | No | The paper mentions the use of LLaMA2 series models and the Adam optimizer but does not provide specific version numbers for any software libraries or frameworks used (e.g., Python, PyTorch, TensorFlow, scikit-learn versions). |
| Experiment Setup | Yes | The hidden layer dimensions of the Feed Forward Network (FFN) and other components are set to 256 and 128, respectively. For the Semantic-aware Tabular Encoder, we use a 2-layer, 8-head transformer, while the knowledge adapter consists of a 2-layer, 2-head transformer. Dropout is set to 0.1. During the meta-learning phase, The Adam optimizer is used for training, with the learning rate set to 1e-4. The activation vector in the LLMs is obtained from the 30 layers. For the fine-tuning phase, the learning rate is reduced to 1e-5 due to the limited number of labeled samples. |