In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model’s expected responses and its intrinsic generation capability. Through the application of IFD, cherry samples can be pinpointed, leading to a marked uptick in model training efficiency. Empirical validations on datasets like Alpaca and WizardLM underpin our findings; with a mere 10% of original data input, our strategy showcases improved results. This synthesis of self-guided cherry-picking and the IFD metric signifies a transformative leap in the instruction tuning of LLMs, promising both efficiency and resource-conscious advancements. Codes, data, and models are available.

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involvement of LLMs in this process. To reduce the filtering cost, we study Superfiltering: Can we use a smaller and weaker model to select data for finetuning a larger and stronger model? Despite the performance gap between weak and strong language models, we find their highly consistent capability to perceive instruction difficulty and data selection results. This enables us to use a much smaller and more efficient model to filter the instruction data used to train a larger language model. Not only does it largely speed up the data filtering, but the filtered-data-finetuned LLM achieves even better performance on standard benchmarks. Extensive experiments validate the efficacy and efficiency of our approach.

The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generators formulate the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their advanced QA capabilities, but they are typically too large to be fine-tuned with budget constraints while some of them are only accessible via APIs. To tackle this issue and further improve ReQA performance, we propose a trainable Pluggable Reward-Driven Contextual Adapter (PRCA), keeping the generator as a black box. Positioned between the retriever and generator in a Pluggable manner, PRCA refines the retrieved information by operating in a token-autoregressive strategy via maximizing rewards of the reinforcement learning phase. Our experiments validate PRCA’s effectiveness in enhancing ReQA performance on three datasets by up to 20% improvement to fit black-box LLMs into existing frameworks, demonstrating its considerable potential in the LLMs era.

This paper shows our submission on the second automatic simultaneous translation workshop at NAACL2021. We participate in all the two directions of Chinese-to-English translation, Chinese audio→English text and Chinese text→English text. We do data filtering and model training techniques to get the best BLEU score and reduce the average lagging. We propose a two-stage simultaneous translation pipeline system which is composed of Quartznet and BPE-based transformer. We propose a competitive simultaneous translation system and achieves a BLEU score of 24.39 in the audio input track.

Federated learning has sparkled new interests in the deep learning society to make use of isolated data sources from independent institutes. With the development of novel training tools, we have successfully deployed federated natural language processing networks on GPU-enabled server clusters. This paper demonstrates federated training of a popular NLP model, TextCNN, with applications in sentence intent classification. Furthermore, differential privacy is introduced to protect participants in the training process, in a manageable manner. Distinguished from previous client-level privacy protection schemes, the proposed differentially private federated learning procedure is defined in the dataset sample level, inherent with the applications among institutions instead of individual users. Optimal settings of hyper-parameters for the federated TextCNN model are studied through comprehensive experiments. We also evaluated the performance of federated TextCNN model under imbalanced data load configuration. Experiments show that, the sampling ratio has a large impact on the performance of the FL models, causing up to 38.4% decrease in the test accuracy, while they are robust to different noise multiplier levels, with less than 3% variance in the test accuracy. It is also found that the FL models are sensitive to data load balancedness among client datasets. When the data load is imbalanced, model performance dropped by up to 10%.