We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website. Existing datasets for web agents either use simulated websites or only cover a limited set of websites and tasks, thus not suitable for generalist web agents. With over 2,000 open-ended tasks collected from 137 websites spanning 31 domains and crowdsourced action sequences for the tasks, Mind2Web provides three necessary ingredients for building generalist web agents: 1) diverse domains, websites, and tasks, 2) use of real-world websites instead of simulated and simplified ones, and 3) a broad spectrum of user interaction patterns. Based on Mind2Web, we conduct an initial exploration of using large language models (LLMs) for building generalist web agents. While the raw HTML of real-world websites are often too large to be fed to LLMs, we show that first filtering it with a small LM significantly improves the effectiveness and efficiency of LLMs. Our solution demonstrates a decent level of performance, even on websites or entire domains the model has never seen before, but there is still a substantial room to improve towards truly generalizable agents. We open-source our dataset, model implementation, and trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further research on building a generalist agent for the web.
This paper studies a new task of federated learning (FL) for semantic parsing, where multiple clients collaboratively train one global model without sharing their semantic parsing data. By leveraging data from multiple clients, the FL paradigm can be especially beneficial for clients that have little training data to develop a data-hungry neural semantic parser on their own. We propose an evaluation setup to study this task, where we re-purpose widely-used single-domain text-to-SQL datasets as clients to form a realistic heterogeneous FL setting and collaboratively train a global model. As standard FL algorithms suffer from the high client heterogeneity in our realistic setup, we further propose a novel LOss Reduction Adjusted Re-weighting (Lorar) mechanism to mitigate the performance degradation, which adjusts each client's contribution to the global model update based on its training loss reduction during each round. Our intuition is that the larger the loss reduction, the further away the current global model is from the client's local optimum, and the larger weight the client should get. By applying Lorar to three widely adopted FL algorithms (FedAvg, FedOPT and FedProx), we observe that their performance can be improved substantially on average (4%-20% absolute gain under MacroAvg) and that clients with smaller datasets enjoy larger performance gains. In addition, the global model converges faster for almost all the clients.
Conventional supervised approaches for text-to-SQL parsing often require large amounts of annotated data, which is costly to obtain in practice. Recently, in-context learning with large language models (LLMs) has caught increasing attention due to its superior few-shot performance in a wide range of tasks. However, most attempts to use in-context learning for text-to-SQL parsing still lag behind supervised methods. We hypothesize that the under-performance is because text-to-SQL parsing requires complex, multi-step reasoning. In this paper, we systematically study how to enhance the reasoning ability of LLMs for text-to-SQL parsing through chain-of-thought (CoT) style promptings including CoT prompting and Least-to-Most prompting. Our experiments demonstrate that iterative prompting as in Least-to-Most prompting may be unnecessary for text-to-SQL parsing and directly applying existing CoT style prompting methods leads to error propagation issues. By improving multi-step reasoning while avoiding much detailed information in the reasoning steps which may lead to error propagation, our new method outperforms existing ones by 2.4 point absolute gains on the Spider development set.
Despite remarkable progress in text-to-SQL semantic parsing in recent years, the performance of existing parsers is still far from perfect. At the same time, modern deep learning based text-to-SQL parsers are often over-confident and thus casting doubt on their trustworthiness when deployed for real use. To that end, we propose to build a parser-independent error detection model for text-to-SQL semantic parsing. The proposed model is based on pre-trained language model of code and is enhanced with structural features learned by graph neural networks. We train our model on realistic parsing errors collected from a cross-domain setting. Experiments with three strong text-to-SQL parsers featuring different decoding mechanisms show that our approach outperforms parser-dependent uncertainty metrics and could effectively improve the performance and usability of text-to-SQL semantic parsers regardless of their architectures.
We explore testing the reasoning ability of large language models (LLMs), such as ChatGPT, by engaging with them in a debate-like conversation that probes deeper into their understanding of the subject. Specifically, we formulate a new task where given a question, the LLM can generate a correct solution while the user believes in a wrong solution in the beginning, and they need to discuss to make the correct decision through dialogue. Such a setting requires the LLM to not only achieve the correct answer on its own (which could be done by shallow memorization), but also be able to defend the truth instead of blindly believing or getting misled by the user's (invalid) arguments and critiques, thus testing in greater depth whether the LLM grasps the essence of the reasoning required to solve the problem. To automate this evaluation framework and save human labor, we simulate the user using another LLM conditioned on a synthesized wrong solution. Across a range of complex reasoning benchmarks spanning math, commonsense, logic and tasks from BIG-Bench, we find that despite being able to generate correct step-by-step solutions in the beginning, ChatGPT cannot maintain its belief in truth for a significant portion of examples when challenged by often-time absurdly invalid arguments. Our work reveals LLMs' weaknesses not captured by conventional benchmarking, and also points to danger zones of aligning models with human feedback.
Despite recent progress in text-to-SQL parsing, current semantic parsers are still not accurate enough for practical use. In this paper, we investigate how to build automatic text-to-SQL error correction models. Noticing that token-level edits are out of context and sometimes ambiguous, we propose building clause-level edit models instead. Besides, while most language models of code are not specifically pre-trained for SQL, they know common data structures and their operations in programming languages such as Python. Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code. Our error correction model improves the exact set match accuracy of different parsers by 2.4-6.5 and obtains up to 4.3 point absolute improvement over two strong baselines. Our code and data are available at https://github.com/OSU-NLP-Group/Auto-SQL-Correction.
A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support their claims. However, evaluating the attribution, i.e., verifying whether the generated statement is indeed fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate the automatic evaluation of attribution by LLMs. We begin by providing a definition of attribution and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks, such as question answering, fact-checking, natural language inference, and summarization. To facilitate the evaluation, we manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on the curated test set and simulated test examples from existing benchmark questions highlight both promising signals as well as remaining challenges for the automatic evaluation of attribution. We hope our testbed, modeling methodology, and insights will help lay the foundation for future studies on this important problem.
Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However, existing methods typically learn soft prompt vectors from scratch, and it has not been clear how to exploit the rich cross-task knowledge with prompt vectors in a multitask learning setting. We propose multitask prompt tuning (MPT), which first learns a single transferable prompt by distilling knowledge from multiple task-specific source prompts. We then learn multiplicative low rank updates to this shared prompt to efficiently adapt it to each downstream target task. Extensive experiments on 23 NLP datasets demonstrate that our proposed approach outperforms the state-of-the-art methods, including the full finetuning baseline in some cases, despite only tuning 0.035% as many task-specific parameters.
Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermediate rationales for solving a problem, by providing a series of reasoning steps in the demonstrations. Despite its success, there is still little understanding of what makes CoT prompting effective and which aspects of the demonstrated reasoning steps contribute to its performance. In this paper, we show that CoT reasoning is possible even with invalid demonstrations - prompting with invalid reasoning steps can achieve over 80-90% of the performance obtained using CoT under various metrics, while still generating coherent lines of reasoning during inference. Further experiments show that other aspects of the rationales, such as being relevant to the query and correctly ordering the reasoning steps, are much more important for effective CoT reasoning. Overall, these findings both deepen our understanding of CoT prompting, and open up new questions regarding LLMs' capability to learn to reason in context.