MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization

Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation with iterative debugging, and a visual feedback mechanism for error correction. To address the lack of benchmarks in this field, we present MatPlotBench, a high-quality benchmark consisting of 100 human-verified test cases. Additionally, we introduce a scoring approach that utilizes GPT-4V for automatic evaluation. Experimental results demonstrate that MatPlotAgent can improve the performance of various LLMs, including both commercial and open-source models. Furthermore, the proposed evaluation method shows a strong correlation with human-annotated scores.

Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems

Large language models (LLMs) have strong capabilities in solving diverse natural language processing tasks. However, the safety and security issues of LLM systems have become the major obstacle to their widespread application. Many studies have extensively investigated risks in LLM systems and developed the corresponding mitigation strategies. Leading-edge enterprises such as OpenAI, Google, Meta, and Anthropic have also made lots of efforts on responsible LLMs. Therefore, there is a growing need to organize the existing studies and establish comprehensive taxonomies for the community. In this paper, we delve into four essential modules of an LLM system, including an input module for receiving prompts, a language model trained on extensive corpora, a toolchain module for development and deployment, and an output module for exporting LLM-generated content. Based on this, we propose a comprehensive taxonomy, which systematically analyzes potential risks associated with each module of an LLM system and discusses the corresponding mitigation strategies. Furthermore, we review prevalent benchmarks, aiming to facilitate the risk assessment of LLM systems. We hope that this paper can help LLM participants embrace a systematic perspective to build their responsible LLM systems.

Privacy-Preserving Prompt Tuning for Large Language Model Services

Prompt tuning provides an efficient way for users to customize Large Language Models (LLMs) with their private data in the emerging LLM service scenario. However, the sensitive nature of private data brings the need for privacy preservation in LLM service customization. Based on prompt tuning, we propose Privacy-Preserving Prompt Tuning (RAPT), a framework that provides privacy guarantees for LLM services. \textsc{rapt} adopts a local privacy setting, allowing users to privatize their data locally with local differential privacy. As prompt tuning performs poorly when directly trained on privatized data, we introduce a novel privatized token reconstruction task that is trained jointly with the downstream task, allowing LLMs to learn better task-dependent representations. Despite the simplicity of our framework, experiments show that RAPT achieves competitive performance across tasks while providing privacy guarantees against adversaries.

Black-box Prompt Tuning with Subspace Learning

Black-box prompt tuning uses derivative-free optimization algorithms to learn prompts in low-dimensional subspaces instead of back-propagating through the network of Large Language Models (LLMs). Recent studies have found that black-box prompt tuning lacks versatility across tasks and LLMs, which we believe is related to the inappropriate choice of subspaces. In this paper, we propose Black-box prompt tuning with Subspace Learning (BSL) to improve the versatility of black-box prompt tuning. Based on the assumption that nearly optimal prompts for similar tasks exist in a common subspace, we propose identifying such subspaces by meta-learning on a set of similar source tasks. Therefore, for a target task that shares similarities with source tasks, we guarantee that optimizing in the subspace can find a prompt that performs well on the target task. Experiments confirm that our BSL framework consistently achieves competitive performance regardless of downstream tasks and LLMs.

A Template-based Method for Constrained Neural Machine Translation

Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose pre-specified constraints into the translation process of NMT models. Although many approaches have been proposed to address this issue, most existing methods can not satisfy the following three desiderata at the same time: (1) high translation quality, (2) high match accuracy, and (3) low latency. In this work, we propose a template-based method that can yield results with high translation quality and match accuracy while keeping the decoding speed. Our basic idea is to rearrange the generation of constrained and unconstrained tokens through a template. The generation and derivation of the template can be learned through one sequence-to-sequence training framework. Thus our method does not require any changes in the model architecture and the decoding algorithm, making it easy to apply. Experimental results show that the proposed template-based methods can outperform several representative baselines in lexically and structurally constrained translation tasks.

A Roadmap for Big Model

With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields. At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research. In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application. We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.

Integrating Vectorized Lexical Constraints for Neural Machine Translation

Lexically constrained neural machine translation (NMT), which controls the generation of NMT models with pre-specified constraints, is important in many practical scenarios. Due to the representation gap between discrete constraints and continuous vectors in NMT models, most existing works choose to construct synthetic data or modify the decoding algorithm to impose lexical constraints, treating the NMT model as a black box. In this work, we propose to open this black box by directly integrating the constraints into NMT models. Specifically, we vectorize source and target constraints into continuous keys and values, which can be utilized by the attention modules of NMT models. The proposed integration method is based on the assumption that the correspondence between keys and values in attention modules is naturally suitable for modeling constraint pairs. Experimental results show that our method consistently outperforms several representative baselines on four language pairs, demonstrating the superiority of integrating vectorized lexical constraints.

MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators

Pre-trained language models have recently been shown to be able to perform translation without finetuning via prompting. Inspired by these findings, we study improving the performance of pre-trained language models on translation tasks, where training neural machine translation models is the current de facto approach. We present Multi-Stage Prompting, a simple and lightweight approach for better adapting pre-trained language models to translation tasks. To make pre-trained language models better translators, we divide the translation process via pre-trained language models into three separate stages: the encoding stage, the re-encoding stage, and the decoding stage. During each stage, we independently apply different continuous prompts for allowing pre-trained language models better adapting to translation tasks. We conduct extensive experiments on low-, medium-, and high-resource translation tasks. Experiments show that our method can significantly improve the translation performance of pre-trained language models.

GraphPiece: Efficiently Generating High-Quality Molecular Graph with Substructures

Molecular graph generation is a fundamental but challenging task in various applications such as drug discovery and material science, which requires generating valid molecules with desired properties. Auto-regressive models, which usually construct graphs following sequential actions of adding nodes and edges at the atom-level, have made rapid progress in recent years. However, these atom-level models ignore high-frequency subgraphs that not only capture the regularities of atomic combination in molecules but also are often related to desired chemical properties. In this paper, we propose a method to automatically discover such common substructures, which we call {\em graph pieces}, from given molecular graphs. Based on graph pieces, we leverage a variational autoencoder to generate molecules in two phases: piece-level graph generation followed by bond completion. Experiments show that our graph piece variational autoencoder achieves better performance over state-of-the-art baselines on property optimization and constrained property optimization tasks with higher computational efficiency.

Language Models are Good Translators

Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of large-scale pre-trained language models on machine translation in a limited scenario, we firstly demonstrate that a single language model (LM4MT) can achieve comparable performance with strong encoder-decoder NMT models on standard machine translation benchmarks, using the same training data and similar amount of model parameters. LM4MT can also easily utilize source-side texts as additional supervision. Though modeling the source- and target-language texts with the same mechanism, LM4MT can provide unified representations for both source and target sentences, which can better transfer knowledge across languages. Extensive experiments on pivot-based and zero-shot translation tasks show that LM4MT can outperform the encoder-decoder NMT model by a large margin.