The Graphical User Interface (GUI) is pivotal for human interaction with the digital world, enabling efficient device control and the completion of complex tasks. Recent progress in Large Language Models (LLMs) and Vision Language Models (VLMs) offers the chance to create advanced GUI agents. To ensure their effectiveness, there's a pressing need for qualified benchmarks that provide trustworthy and reproducible evaluations -- a challenge current benchmarks often fail to address. To tackle this issue, we introduce Mobile-Env, a comprehensive toolkit tailored for creating GUI benchmarks in the Android mobile environment. Mobile-Env offers an isolated and controllable setting for reliable evaluations, and accommodates intermediate instructions and rewards to reflect real-world usage more naturally. Utilizing Mobile-Env, we collect an open-world task set across various real-world apps and a fixed world set, WikiHow, which captures a significant amount of dynamic online contents for fully controllable and reproducible evaluation. We conduct comprehensive evaluations of LLM agents using these benchmarks. Our findings reveal that even advanced models (e.g., GPT-4V and LLaMA-3) struggle with tasks that are relatively simple for humans. This highlights a crucial gap in current models and underscores the importance of developing more capable foundation models and more effective GUI agent frameworks.
We investigated the capability of the GPT-3.5 large language model (LLM) to operationalize natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior in two social dilemmas: the repeated Prisoners Dilemma and the one-shot Dictator Game. Using a within-subject experimental design, we used a prompt to describe the task environment using a similar protocol to that used in experimental psychology studies with human subjects. We tested our research question by manipulating the part of our prompt which was used to create a simulated persona with different cooperative and competitive stances. We then assessed the resulting simulacras' level of cooperation in each social dilemma, taking into account the effect of different partner conditions for the repeated game. Our results provide evidence that LLMs can, to some extent, translate natural language descriptions of different cooperative stances into corresponding descriptions of appropriate task behaviour, particularly in the one-shot game. There is some evidence of behaviour resembling conditional reciprocity for the cooperative simulacra in the repeated game, and for the later version of the model there is evidence of altruistic behaviour. Our study has potential implications for using LLM chatbots in task environments that involve cooperation, e.g. using chatbots as mediators and facilitators in public-goods negotiations.
Temporal Knowledge graph completion (TKGC) is a crucial task that involves reasoning at known timestamps to complete the missing part of facts and has attracted more and more attention in recent years. Most existing methods focus on learning representations based on graph neural networks while inaccurately extracting information from timestamps and insufficiently utilizing the implied information in relations. To address these problems, we propose a novel TKGC model, namely Pre-trained Language Model with Prompts for TKGC (PPT). We convert a series of sampled quadruples into pre-trained language model inputs and convert intervals between timestamps into different prompts to make coherent sentences with implicit semantic information. We train our model with a masking strategy to convert TKGC task into a masked token prediction task, which can leverage the semantic information in pre-trained language models. Experiments on three benchmark datasets and extensive analysis demonstrate that our model has great competitiveness compared to other models with four metrics. Our model can effectively incorporate information from temporal knowledge graphs into the language models.
The automatic generation of educational questions will play a key role in scaling online education, enabling self-assessment at scale when a global population is manoeuvring their personalised learning journeys. We develop \textit{EduQG}, a novel educational question generation model built by adapting a large language model. Our extensive experiments demonstrate that \textit{EduQG} can produce superior educational questions by further pre-training and fine-tuning a pre-trained language model on the scientific text and science question data.
Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the capacity to handle knowledge-intensive NLP tasks alone; thus, several works have attempted to integrate external knowledge into PLMs. However, despite the promising outcome, we empirically observe that PLMs may have already encoded rich knowledge in their pre-trained parameters but fail to fully utilize them when applying them to knowledge-intensive tasks. In this paper, we propose a new paradigm dubbed Knowledge Rumination to help the pre-trained language model utilize that related latent knowledge without retrieving it from the external corpus. By simply adding a prompt like "As far as I know" to the PLMs, we try to review related latent knowledge and inject them back into the model for knowledge consolidation. We apply the proposed knowledge rumination to various language models, including RoBERTa, DeBERTa, and GPT-3. Experimental results on six commonsense reasoning tasks and GLUE benchmarks demonstrate the effectiveness of our proposed approach, which proves that the knowledge stored in PLMs can be better exploited to enhance performance. Code is available in https://github.com/zjunlp/knowledge-rumination.
Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic embedding space, where the embeddings of high-frequency words are clustered but those of low-frequency words disperse sparsely. This anisotropic phenomenon results in two problems of similarity bias and information bias, lowering the quality of sentence embeddings. To solve the problems, we fine-tune PLMs by leveraging the frequency information of words and propose a novel USRL framework, namely Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering (SLT-FAI). We calculate the word frequencies over the pre-training corpora of PLMs and assign words thresholding frequency labels. With them, (1) we incorporate a similarity discriminator used to distinguish the embeddings of high-frequency and low-frequency words, and adversarially tune the PLM with it, enabling to achieve uniformly frequency-invariant embedding space; and (2) we propose a novel incomplete sentence detection task, where we incorporate an information discriminator to distinguish the embeddings of original sentences and incomplete sentences by randomly masking several low-frequency words, enabling to emphasize the more informative low-frequency words. Our SLT-FAI is a flexible and plug-and-play framework, and it can be integrated with existing USRL techniques. We evaluate SLT-FAI with various backbones on benchmark datasets. Empirical results indicate that SLT-FAI can be superior to the existing USRL baselines. Our code is released in \url{https://github.com/wangbing1416/SLT-FAI}.
The Imaging Data Commons (IDC) is a cloud-based database that provides researchers with open access to cancer imaging data, with the goal of facilitating collaboration. However, cohort discovery within the IDC database has a significant technical learning curve. Recently, large language models (LLM) have demonstrated exceptional utility for natural language processing tasks. We developed Text2Cohort, a LLM-powered toolkit to facilitate user-friendly natural language cohort discovery in the IDC. Our method translates user input into IDC queries using grounding techniques and returns the query's response. We evaluate Text2Cohort on 50 natural language inputs, from information extraction to cohort discovery. Our toolkit successfully generated responses with an 88% accuracy and 0.94 F1 score. We demonstrate that Text2Cohort can enable researchers to discover and curate cohorts on IDC with high levels of accuracy using natural language in a more intuitive and user-friendly way.
The remarkable achievements of Large Language Models (LLMs) have led to the emergence of a novel recommendation paradigm -- Recommendation via LLM (RecLLM). Nevertheless, it is important to note that LLMs may contain social prejudices, and therefore, the fairness of recommendations made by RecLLM requires further investigation. To avoid the potential risks of RecLLM, it is imperative to evaluate the fairness of RecLLM with respect to various sensitive attributes on the user side. Due to the differences between the RecLLM paradigm and the traditional recommendation paradigm, it is problematic to directly use the fairness benchmark of traditional recommendation. To address the dilemma, we propose a novel benchmark called Fairness of Recommendation via LLM (FaiRLLM). This benchmark comprises carefully crafted metrics and a dataset that accounts for eight sensitive attributes1 in two recommendation scenarios: music and movies. By utilizing our FaiRLLM benchmark, we conducted an evaluation of ChatGPT and discovered that it still exhibits unfairness to some sensitive attributes when generating recommendations. Our code and dataset can be found at https://github.com/jizhi-zhang/FaiRLLM.
In this work, we conduct a detailed analysis on the performance of legal-oriented pre-trained language models (PLMs). We examine the interplay between their original objective, acquired knowledge, and legal language understanding capacities which we define as the upstream, probing, and downstream performance, respectively. We consider not only the models' size but also the pre-training corpora used as important dimensions in our study. To this end, we release a multinational English legal corpus (LeXFiles) and a legal knowledge probing benchmark (LegalLAMA) to facilitate training and detailed analysis of legal-oriented PLMs. We release two new legal PLMs trained on LeXFiles and evaluate them alongside others on LegalLAMA and LexGLUE. We find that probing performance strongly correlates with upstream performance in related legal topics. On the other hand, downstream performance is mainly driven by the model's size and prior legal knowledge which can be estimated by upstream and probing performance. Based on these findings, we can conclude that both dimensions are important for those seeking the development of domain-specific PLMs.
The success of large language models (LLMs) has inspired an emerging research field of multimodal learning. However, a grand challenge of exploiting LLMs for multimodal learning is the size of pre-trained LLMs which are always with billions of parameters. To tackle this challenge, models such as MiniGPT-4 and LLaVA have been developed to fine-tune the pre-trained models using fewer parameters. Despite their promising performance, these models remain limited in their understanding of artistic imagery. To facilitate better artistic-understanding, in this paper, we propose ArtGPT-4, a pioneering large vision-language model tailored to address the limitations of existing models in artistic comprehension. The key innovation of ArtGPT-4 lies in its craft for the sophisticated challenge of artistic image comprehension, setting it apart from other models that overlook fine details for broader themes. Specifically, it works by integrating some specialized adapter layers into the LLM, enabling the model to more efficiently and effectively parse and interpret complex visual tokens, instead of fine-tuning the whole LLM as in the existing method. ArtGPT-4 has demonstrated its outstanding performance on the efficiency: utilizing a Tesla A100 device, its training can be completed in mere 2 hours with an image-text pair dataset comprising approximately 0.52M entries. Additionally, ArtGPT-4 has also achieved state-of-the-art performance on the ArtEmis and ArtEmis-v2.0 datasets as well as the benchmarks established in this work, lagging behind professional artists' descriptions by a negligible 0.15 points on a 6-point scale. The outstanding performance of ArtGPT-4 shows that it can render images with an artistic-understanding and convey the emotions they inspire, mirroring human interpretation. The code and the pre-trained model are accessible in \url{https://github.com/DLYuanGod/ArtGPT-4}.
Dialogue systems for non-English languages have long been under-explored. In this paper, we take the first step to investigate few-shot cross-lingual transfer learning (FS-XLT) and multitask learning (MTL) in the context of open-domain dialogue generation for non-English languages with limited data. We observed catastrophic forgetting in both FS-XLT and MTL for all 6 languages in our preliminary experiments. To mitigate the issue, we propose a simple yet effective prompt learning approach that can preserve the multilinguality of multilingual pre-trained language model (mPLM) in FS-XLT and MTL by bridging the gap between pre-training and fine-tuning with Fixed-prompt LM Tuning and our hand-crafted prompts. Experimental results on all 6 languages in terms of both automatic and human evaluations demonstrate the effectiveness of our approach. Our code is available at https://github.com/JeremyLeiLiu/XLinguDial.
Large language models (LLMs) like GPT-4 have recently demonstrated impressive capabilities in natural language understanding and generation. However, there is a concern that they can be misused for malicious purposes, such as fraud or denial-of-service attacks. Therefore, it is crucial to develop methods for detecting whether the party involved in a conversation is a bot or a human. In this paper, we propose a framework named FLAIR, Finding Large Language Model Authenticity via a Single Inquiry and Response, to detect conversational bots in an online manner. Specifically, we target a single question scenario that can effectively differentiate human users from bots. The questions are divided into two categories: those that are easy for humans but difficult for bots (e.g., counting, substitution, searching, and ASCII art reasoning), and those that are easy for bots but difficult for humans (e.g., memorization and computation). Our approach shows different strengths of these questions in their effectiveness, providing a new way for online service providers to protect themselves against nefarious activities. Our code and question set are available at https://github.com/hongwang600/FLAIR.
We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer. The integration of knowledge across heterogeneous tasks is enabled by a novel feature called Task Explanation Prompt (TEP). With rich and structured information such as task input/output format, TEP reduces interference among tasks, allowing the model to focus on their shared structure. With a single model, Musketeer achieves results comparable to or better than strong baselines trained on single tasks, almost uniformly across multiple tasks.
Recommendation foundation model utilizes large language models (LLM) for recommendation by converting recommendation tasks into natural language tasks. It enables generative recommendation which directly generates the item(s) to recommend rather than calculating a ranking score for each and every candidate item as in traditional recommendation models, simplifying the recommendation pipeline from multi-stage filtering to single-stage filtering. To avoid generating excessively long text and hallucinated recommendations when deciding which item(s) to recommend, creating LLM-compatible item IDs to uniquely identify each item is essential for recommendation foundation models. In this study, we systematically examine the item ID creation and indexing problem for recommendation foundation models, using P5 as an example of the backbone LLM. To emphasize the importance of item indexing, we first discuss the issues of several trivial item indexing methods, such as random indexing, title indexing, and independent indexing. We then propose four simple yet effective solutions, including sequential indexing, collaborative indexing, semantic (content-based) indexing, and hybrid indexing. Our study highlights the significant influence of item indexing methods on the performance of LLM-based recommendation, and our results on real-world datasets validate the effectiveness of our proposed solutions. The research also demonstrates how recent advances on language modeling and traditional IR principles such as indexing can help each other for better learning and inference. Source code and data are available at https://github.com/Wenyueh/LLM-RecSys-ID.
Real-world data often have an open long-tailed distribution, and building a unified QA model supporting various tasks is vital for practical QA applications. However, it is non-trivial to extend previous QA approaches since they either require access to seen tasks of adequate samples or do not explicitly model samples from unseen tasks. In this paper, we define Open Long-Tailed QA (OLTQA) as learning from long-tailed distributed data and optimizing performance over seen and unseen QA tasks. We propose an OLTQA model that encourages knowledge sharing between head, tail and unseen tasks, and explicitly mines knowledge from a large pre-trained language model (LM). Specifically, we organize our model through a pool of fine-grained components and dynamically combine these components for an input to facilitate knowledge sharing. A retrieve-then-rerank frame is further introduced to select in-context examples, which guild the LM to generate text that express knowledge for QA tasks. Moreover, a two-stage training approach is introduced to pre-train the framework by knowledge distillation (KD) from the LM and then jointly train the frame and a QA model through an adaptive mutual KD method. On a large-scale OLTQA dataset we curate from 43 existing QA datasets, our model consistently outperforms the state-of-the-art. We release the code and data at \url{https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/oltqa}.
Lifelong learning (LL) is an important ability for NLP models to learn new tasks continuously. Architecture-based approaches are reported to be effective implementations for LL models. However, it is non-trivial to extend previous approaches to domain incremental LL scenarios since they either require access to task identities in the testing phase or cannot handle samples from unseen tasks. In this paper, we propose \textbf{Diana}: a \underline{d}ynam\underline{i}c \underline{a}rchitecture-based lifelo\underline{n}g le\underline{a}rning model that tries to learn a sequence of tasks with a prompt-enhanced language model. Four types of hierarchically organized prompts are used in Diana to capture knowledge from different granularities. Specifically, we dedicate task-level prompts to capture task-specific knowledge to retain high LL performances and maintain instance-level prompts to learn knowledge shared across input samples to improve the model's generalization performance. Moreover, we dedicate separate prompts to explicitly model unseen tasks and introduce a set of prompt key vectors to facilitate knowledge sharing between tasks. Extensive experiments demonstrate that Diana outperforms state-of-the-art LL models, especially in handling unseen tasks. We release the code and data at \url{https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/diana}.
A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether the generated statement is 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 given by LLMs. We begin by defining different types of attribution errors, 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. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on this curated test set and simulated examples from existing benchmarks highlight both promising signals and challenges. We hope our problem formulation, testbeds, and findings will help lay the foundation for future studies on this important problem.
Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge. However, negative knowledge, such as "lions don't live in the ocean", is also ubiquitous in the world but rarely mentioned explicitly in the text. What do LLMs know about negative knowledge? This work examines the ability of LLMs to negative commonsense knowledge. We design a constrained keywords-to-sentence generation task (CG) and a Boolean question-answering task (QA) to probe LLMs. Our experiments reveal that LLMs frequently fail to generate valid sentences grounded in negative commonsense knowledge, yet they can correctly answer polar yes-or-no questions. We term this phenomenon the belief conflict of LLMs. Our further analysis shows that statistical shortcuts and negation reporting bias from language modeling pre-training cause this conflict.
We report a flexible language-model based deep learning strategy, applied here to solve complex forward and inverse problems in protein modeling, based on an attention neural network that integrates transformer and graph convolutional architectures in a causal multi-headed graph mechanism, to realize a generative pretrained model. The model is applied to predict secondary structure content (per-residue level and overall content), protein solubility, and sequencing tasks. Further trained on inverse tasks, the model is rendered capable of designing proteins with these properties as target features. The model is formulated as a general framework, completely prompt-based, and can be adapted for a variety of downstream tasks. We find that adding additional tasks yields emergent synergies that the model exploits in improving overall performance, beyond what would be possible by training a model on each dataset alone. Case studies are presented to validate the method, yielding protein designs specifically focused on structural proteins, but also exploring the applicability in the design of soluble, antimicrobial biomaterials. While our model is trained to ultimately perform 8 distinct tasks, with available datasets it can be extended to solve additional problems. In a broader sense, this work illustrates a form of multiscale modeling that relates a set of ultimate building blocks (here, byte-level utf8 characters that define the nature of the physical system at hand) to complex output. This materiomic scheme captures complex emergent relationships between universal building block and resulting properties via a synergizing learning capacity to express a set of potentialities embedded in the knowledge used in training, via the interplay of universality and diversity.
We present an interactive visual framework named InternGPT, or iGPT for short. The framework integrates chatbots that have planning and reasoning capabilities, such as ChatGPT, with non-verbal instructions like pointing movements that enable users to directly manipulate images or videos on the screen. Pointing (including gestures, cursors, etc.) movements can provide more flexibility and precision in performing vision-centric tasks that require fine-grained control, editing, and generation of visual content. The name InternGPT stands for \textbf{inter}action, \textbf{n}onverbal, and \textbf{chat}bots. Different from existing interactive systems that rely on pure language, by incorporating pointing instructions, the proposed iGPT significantly improves the efficiency of communication between users and chatbots, as well as the accuracy of chatbots in vision-centric tasks, especially in complicated visual scenarios where the number of objects is greater than 2. Additionally, in iGPT, an auxiliary control mechanism is used to improve the control capability of LLM, and a large vision-language model termed Husky is fine-tuned for high-quality multi-modal dialogue (impressing ChatGPT-3.5-turbo with 93.89\% GPT-4 Quality). We hope this work can spark new ideas and directions for future interactive visual systems. Welcome to watch the code at https://github.com/OpenGVLab/InternGPT.