Automated essay scoring (AES) provides a useful tool for students and instructors in writing classes by generating essay scores in real-time. However, previous AES models do not provide more specific rubric-based scores nor feedback on how to improve the essays, which can be even more important than the overall scores for learning. We present FABRIC, a pipeline to help students and instructors in English writing classes by automatically generating 1) the overall scores, 2) specific rubric-based scores, and 3) detailed feedback on how to improve the essays. Under the guidance of English education experts, we chose the rubrics for the specific scores as content, organization, and language. The first component of the FABRIC pipeline is DREsS, a real-world Dataset for Rubric-based Essay Scoring (DREsS). The second component is CASE, a Corruption-based Augmentation Strategy for Essays, with which we can improve the accuracy of the baseline model by 45.44%. The third component is EssayCoT, the Essay Chain-of-Thought prompting strategy which uses scores predicted from the AES model to generate better feedback. We evaluate the effectiveness of the new dataset DREsS and the augmentation strategy CASE quantitatively and show significant improvements over the models trained with existing datasets. We evaluate the feedback generated by EssayCoT with English education experts to show significant improvements in the helpfulness of the feedback across all rubrics. Lastly, we evaluate the FABRIC pipeline with students in a college English writing class who rated the generated scores and feedback with an average of 6 on the Likert scale from 1 to 7.

Programming has always been at the heart of technological innovation in the 21st century. With the advent of blockchain technologies and the proliferation of web3 paradigms of decentralised applications, smart contracts have been very instrumental in enabling developers to build applications that reside on decentralised blockchains. Despite the huge interest and potential of smart contracts, there is still a significant knowledge and skill gap that developers need to cross in order to build web3 applications. In light of this, we introduce MazzumaGPT, a large language model that has been optimised to generate smart contract code and aid developers to scaffold development and improve productivity. As part of this research, we outline the optimisation and fine-tuning parameters, evaluate the model's performance on functional correctness and address the limitations and broader impacts of our research.

Large language models (LLMs) have recently driven striking performance improvements across a range of natural language processing tasks. The factual knowledge acquired during pretraining and instruction tuning can be useful in various downstream tasks, such as question answering, and language generation. Unlike conventional Knowledge Bases (KBs) that explicitly store factual knowledge, LLMs implicitly store facts in their parameters. Content generated by the LLMs can often exhibit inaccuracies or deviations from the truth, due to facts that can be incorrectly induced or become obsolete over time. To this end, we aim to comprehensively evaluate the extent and scope of factual knowledge within LLMs by designing the benchmark Pinocchio. Pinocchio contains 20K diverse factual questions that span different sources, timelines, domains, regions, and languages. Furthermore, we investigate whether LLMs are able to compose multiple facts, update factual knowledge temporally, reason over multiple pieces of facts, identify subtle factual differences, and resist adversarial examples. Extensive experiments on different sizes and types of LLMs show that existing LLMs still lack factual knowledge and suffer from various spurious correlations. We believe this is a critical bottleneck for realizing trustworthy artificial intelligence. The dataset Pinocchio and our codes will be publicly available.

Large Language Models (LLMs), renowned for their remarkable performance, present a challenge due to their colossal model size when it comes to practical deployment. In response to this challenge, efforts have been directed toward the application of traditional network pruning techniques to LLMs, uncovering a massive number of parameters can be pruned in one-shot without hurting performance. Building upon insights gained from pre-LLM models, prevailing LLM pruning strategies have consistently adhered to the practice of uniformly pruning all layers at equivalent sparsity. However, this observation stands in contrast to the prevailing trends observed in the field of vision models, where non-uniform layerwise sparsity typically yields substantially improved results. To elucidate the underlying reasons for this disparity, we conduct a comprehensive analysis of the distribution of token features within LLMs. In doing so, we discover a strong correlation with the emergence of outliers, defined as features exhibiting significantly greater magnitudes compared to their counterparts in feature dimensions. Inspired by this finding, we introduce a novel LLM pruning methodology that incorporates a tailored set of non-uniform layerwise sparsity ratios specifically designed for LLM pruning, termed as Outlier Weighed Layerwise sparsity (OWL). The sparsity ratio of OWL is directly proportional to the outlier ratio observed within each layer, facilitating a more effective alignment between layerwise weight sparsity and outlier ratios. Our empirical evaluation, conducted across the LLaMA-V1 family and OPT, spanning various benchmarks, demonstrates the distinct advantages offered by OWL over previous methods. For instance, our approach exhibits a remarkable performance gain, surpassing the state-of-the-art Wanda and SparseGPT by 61.22 and 6.80 perplexity at a high sparsity level of 70%, respectively.

The rampant proliferation of large language models, fluent enough to generate text indistinguishable from human-written language, gives unprecedented importance to the detection of machine-generated text. This work is motivated by an important research question: How will the detectors of machine-generated text perform on outputs of a new generator, that the detectors were not trained on? We begin by collecting generation data from a wide range of LLMs, and train neural detectors on data from each generator and test its performance on held-out generators. While none of the detectors can generalize to all generators, we observe a consistent and interesting pattern that the detectors trained on data from a medium-size LLM can zero-shot generalize to the larger version. As a concrete application, we demonstrate that robust detectors can be built on an ensemble of training data from medium-sized models.

Large language models (LLMs) have shown nearly saturated performance on many natural language processing (NLP) tasks. As a result, it is natural for people to believe that LLMs have also mastered abilities such as time understanding and reasoning. However, research on the temporal sensitivity of LLMs has been insufficiently emphasized. To fill this gap, this paper constructs Multiple Sensitive Factors Time QA (MenatQA), which encompasses three temporal factors (scope factor, order factor, counterfactual factor) with total 2,853 samples for evaluating the time comprehension and reasoning abilities of LLMs. This paper tests current mainstream LLMs with different parameter sizes, ranging from billions to hundreds of billions. The results show most LLMs fall behind smaller temporal reasoning models with different degree on these factors. In specific, LLMs show a significant vulnerability to temporal biases and depend heavily on the temporal information provided in questions. Furthermore, this paper undertakes a preliminary investigation into potential improvement strategies by devising specific prompts and leveraging external tools. These approaches serve as valuable baselines or references for future research endeavors.

Large Language Models (LLMs) have demonstrated remarkable progress in utilizing tools, but their closed-source nature and high inference costs pose limitations on their adaptability, necessitating a valid method that leverages smaller, open-sourced models. In this paper, we introduce Toolink, a comprehensive framework that performs task-solving by first creating a toolkit and then integrating the planning and calling of tools through a chain-of-solving (CoS) approach. We first validate the efficacy of Toolink in harnessing the model's creativity and CoS ability on ChatGPT. Subsequently, we curate CoS-GPT, a chain-of-solving dataset designed for tool-using, and finetune the LLaMA-7B model. It results in LLaMA-CoS, a powerful open-source model with advanced tool-planning and tool-calling capabilities. Evaluation on diverse tasks from BIG-bench demonstrates its CoS ability matches that of ChatGPT while its performance surpasses the chain-of-thought approach. Further studies highlight the generalization of LLaMA-CoS to unseen tasks and showcase its capability in using toolkits not explicitly tailored for the target task, affirming its robustness in real-world scenarios. All codes and data are released.

Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two categories. One is to retrieve from an external knowledge base, and the other is to utilize large language models to generate documents. We propose an iterative retrieval-generation collaborative framework. It is not only able to leverage both parametric and non-parametric knowledge, but also helps to find the correct reasoning path through retrieval-generation interactions, which is very important for tasks that require multi-step reasoning. We conduct experiments on four question answering datasets, including single-hop QA and multi-hop QA tasks. Empirical results show that our method significantly improves the reasoning ability of large language models and outperforms previous baselines.

We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents. Using the flexibility of LLMs to be prompted to do various novel tasks using zero-shot, few-shot, context-grounded prompting, we explore the feasibility of using LLMs to solve the ARC Challenge. We firstly convert the input image into multiple suitable text-based abstraction spaces. We then utilise the associative power of LLMs to derive the input-output relationship and map this to actions in the form of a working program, similar to Voyager / Ghost in the MineCraft. In addition, we use iterative environmental feedback in order to guide LLMs to solve the task. Our proposed approach achieves 50 solves out of 111 training set problems (45%) with just three abstraction spaces - grid, object and pixel - and we believe that with more abstraction spaces and learnable actions, we will be able to solve more.

When personalized federated learning (FL) meets large foundation models, new challenges arise from various limitations in resources. In addition to typical limitations such as data, computation, and communication costs, access to the models is also often limited. This paper endeavors to solve both the challenges of limited resources and personalization. PFL that uses Zeroth-Order Optimization for Personalized Federated Learning. PFL avoids direct interference with the foundation models and instead learns to adapt its inputs through zeroth-order optimization. In addition, we employ simple yet effective linear projections to remap its predictions for personalization. To reduce the computation costs and enhance personalization, we propose input surgery to incorporate an auto-encoder with low-dimensional and client-specific embeddings. PFL to analyze its convergence. Extensive empirical experiments on computer vision and natural language processing tasks using popular foundation models demonstrate its effectiveness for FL on black-box foundation models. In recent years, the growing emphasis on data privacy and security has led to the emergence of federated learning (FL) (Warnat-Herresthal et al., 2021; Chen & Chao, 2022; Chen et al., 2023b; Castiglia et al., 2023; Rodríguez-Barroso et al., 2023; Kuang et al., 2023). FL enables collaborative learning while safeguarding data privacy and security across distributed clients (Yang et al., 2019). However, FL faces two key challenges: limited resources and distribution shifts (Figure 1 (a, b)). The rise of large foundation models (Bommasani et al., 2021) has amplified these challenges. The computational demands and communication costs associated with such models hinder the deployment of existing FL approaches (Figure 1a).