2023-04-21 更新
MixPro: Simple yet Effective Data Augmentation for Prompt-based Learning
Authors:Bohan Li, Longxu Dou, Yutai Hou, Yunlong Feng, Honglin Mu, Wanxiang Che
Prompt-based learning reformulates downstream tasks as cloze problems by combining the original input with a template. This technique is particularly useful in few-shot learning, where a model is trained on a limited amount of data. However, the limited templates and text used in few-shot prompt-based learning still leave significant room for performance improvement. Additionally, existing methods using model ensembles can constrain the model efficiency. To address these issues, we propose an augmentation method called MixPro, which augments both the vanilla input text and the templates through token-level, sentence-level, and epoch-level Mixup strategies. We conduct experiments on five few-shot datasets, and the results show that MixPro outperforms other augmentation baselines, improving model performance by an average of 5.08% compared to before augmentation.
PDF Under review at the Frontiers of Computer Science (https://www.springer.com/journal/11704/); 14 pages, 4 figures, 5 tables
点此查看论文截图
GeneGPT: Teaching Large Language Models to Use NCBI Web APIs
Authors:Qiao Jin, Yifan Yang, Qingyu Chen, Zhiyong Lu
In this paper, we present GeneGPT, a novel method for teaching large language models (LLMs) to use the Web Application Programming Interfaces (APIs) of the National Center for Biotechnology Information (NCBI) and answer genomics questions. Specifically, we prompt Codex (code-davinci-002) to solve the GeneTuring tests with few-shot URL requests of NCBI API calls as demonstrations for in-context learning. During inference, we stop the decoding once a call request is detected and make the API call with the generated URL. We then append the raw execution results returned by NCBI APIs to the generated texts and continue the generation until the answer is found or another API call is detected. Our preliminary results show that GeneGPT achieves state-of-the-art results on three out of four one-shot tasks and four out of five zero-shot tasks in the GeneTuring dataset. Overall, GeneGPT achieves a macro-average score of 0.76, which is much higher than retrieval-augmented LLMs such as the New Bing (0.44), biomedical LLMs such as BioMedLM (0.08) and BioGPT (0.04), as well as other LLMs such as GPT-3 (0.16) and ChatGPT (0.12).
PDF Work in progress
点此查看论文截图
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
Authors:Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Jianfeng Gao
Large language models (LLMs) have achieved remarkable progress in various natural language processing tasks with emergent abilities. However, they face inherent limitations, such as an inability to access up-to-date information, utilize external tools, or perform precise mathematical reasoning. In this paper, we introduce Chameleon, a plug-and-play compositional reasoning framework that augments LLMs to help address these challenges. Chameleon synthesizes programs to compose various tools, including LLM models, off-the-shelf vision models, web search engines, Python functions, and rule-based modules tailored to user interests. Built on top of an LLM as a natural language planner, Chameleon infers the appropriate sequence of tools to compose and execute in order to generate a final response. We showcase the adaptability and effectiveness of Chameleon on two tasks: ScienceQA and TabMWP. Notably, Chameleon with GPT-4 achieves an 86.54% accuracy on ScienceQA, significantly improving upon the best published few-shot model by 11.37%; using GPT-4 as the underlying LLM, Chameleon achieves a 17.8% increase over the state-of-the-art model, leading to a 98.78% overall accuracy on TabMWP. Further studies suggest that using GPT-4 as a planner exhibits more consistent and rational tool selection and is able to infer potential constraints given the instructions, compared to other LLMs like ChatGPT.
PDF 25 pages, 10 figures. Project page: https://chameleon-llm.github.io
点此查看论文截图
Clustered-patch Element Connection for Few-shot Learning
Authors:Jinxiang Lai, Siqian Yang, Junhong Zhou, Wenlong Wu, Xiaochen Chen, Jun Liu, Bin-Bin Gao, Chengjie Wang
Weak feature representation problem has influenced the performance of few-shot classification task for a long time. To alleviate this problem, recent researchers build connections between support and query instances through embedding patch features to generate discriminative representations. However, we observe that there exists semantic mismatches (foreground/ background) among these local patches, because the location and size of the target object are not fixed. What is worse, these mismatches result in unreliable similarity confidences, and complex dense connection exacerbates the problem. According to this, we propose a novel Clustered-patch Element Connection (CEC) layer to correct the mismatch problem. The CEC layer leverages Patch Cluster and Element Connection operations to collect and establish reliable connections with high similarity patch features, respectively. Moreover, we propose a CECNet, including CEC layer based attention module and distance metric. The former is utilized to generate a more discriminative representation benefiting from the global clustered-patch features, and the latter is introduced to reliably measure the similarity between pair-features. Extensive experiments demonstrate that our CECNet outperforms the state-of-the-art methods on classification benchmark. Furthermore, our CEC approach can be extended into few-shot segmentation and detection tasks, which achieves competitive performances.
PDF
点此查看论文截图
Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?
Authors:Haoyang Peng, Baopu Li, Bo Zhang, Xin Chen, Tao Chen, Hongyuan Zhu
Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural language processing, this work proposes a novel Multi-view Vision-Prompt Fusion Network (MvNet) for few-shot 3D point cloud classification. MvNet investigates the possibility of leveraging the off-the-shelf 2D pre-trained models to achieve the few-shot classification, which can alleviate the over-dependence issue of the existing baseline models towards the large-scale annotated 3D point cloud data. Specifically, MvNet first encodes a 3D point cloud into multi-view image features for a number of different views. Then, a novel multi-view prompt fusion module is developed to effectively fuse information from different views to bridge the gap between 3D point cloud data and 2D pre-trained models. A set of 2D image prompts can then be derived to better describe the suitable prior knowledge for a large-scale pre-trained image model for few-shot 3D point cloud classification. Extensive experiments on ModelNet, ScanObjectNN, and ShapeNet datasets demonstrate that MvNet achieves new state-of-the-art performance for 3D few-shot point cloud image classification. The source code of this work will be available soon.
PDF 10 pages,5 figures
点此查看论文截图
SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning
Authors:Lingyuan Meng, Ke Liang, Bin Xiao, Sihang Zhou, Yue Liu, Meng Liu, Xihong Yang, Xinwang Liu
Few-shot relation reasoning on knowledge graphs (FS-KGR) aims to infer long-tail data-poor relations, which has drawn increasing attention these years due to its practicalities. The pre-training of previous methods needs to manually construct the meta-relation set, leading to numerous labor costs. Self-supervised learning (SSL) is treated as a solution to tackle the issue, but still at an early stage for FS-KGR task. Moreover, most of the existing methods ignore leveraging the beneficial information from aliasing relations (AR), i.e., data-rich relations with similar contextual semantics to the target data-poor relation. Therefore, we proposed a novel Self-Supervised Learning model by leveraging Aliasing Relations to assist FS-KGR, termed SARF. Concretely, four main components are designed in our model, i.e., SSL reasoning module, AR-assisted mechanism, fusion module, and scoring function. We first generate the representation of the co-occurrence patterns in a generative manner. Meanwhile, the representations of aliasing relations are learned to enhance reasoning in the AR-assist mechanism. Besides, multiple strategies, i.e., simple summation and learnable fusion, are offered for representation fusion. Finally, the generated representation is used for scoring. Extensive experiments on three few-shot benchmarks demonstrate that SARF achieves state-of-the-art performance compared with other methods in most cases.
PDF This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
点此查看论文截图
SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation
Authors:Nikos Athanasiou, Mathis Petrovich, Michael J. Black, Gül Varol
Our goal is to synthesize 3D human motions given textual inputs describing simultaneous actions, for example ‘waving hand’ while ‘walking’ at the same time. We refer to generating such simultaneous movements as performing ‘spatial compositions’. In contrast to temporal compositions that seek to transition from one action to another, spatial compositing requires understanding which body parts are involved in which action, to be able to move them simultaneously. Motivated by the observation that the correspondence between actions and body parts is encoded in powerful language models, we extract this knowledge by prompting GPT-3 with text such as “what are the body parts involved in the action
PDF arXiv version
点此查看论文截图
GPT-NER: Named Entity Recognition via Large Language Models
Authors:Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, Guoyin Wang
Despite the fact that large-scale Language Models (LLM) have achieved SOTA performances on a variety of NLP tasks, its performance on NER is still significantly below supervised baselines. This is due to the gap between the two tasks the NER and LLMs: the former is a sequence labeling task in nature while the latter is a text-generation model. In this paper, we propose GPT-NER to resolve this issue. GPT-NER bridges the gap by transforming the sequence labeling task to a generation task that can be easily adapted by LLMs e.g., the task of finding location entities in the input text “Columbus is a city” is transformed to generate the text sequence “@@Columbus## is a city”, where special tokens @@## marks the entity to extract. To efficiently address the “hallucination” issue of LLMs, where LLMs have a strong inclination to over-confidently label NULL inputs as entities, we propose a self-verification strategy by prompting LLMs to ask itself whether the extracted entities belong to a labeled entity tag. We conduct experiments on five widely adopted NER datasets, and GPT-NER achieves comparable performances to fully supervised baselines, which is the first time as far as we are concerned. More importantly, we find that GPT-NER exhibits a greater ability in the low-resource and few-shot setups, when the amount of training data is extremely scarce, GPT-NER performs significantly better than supervised models. This demonstrates the capabilities of GPT-NER in real-world NER applications where the number of labeled examples is limited.
PDF
点此查看论文截图