Personalized text generation is an emerging research area that has attracted much attention in recent years. Most studies in this direction focus on a particular domain by designing bespoke features or models. In this work, we propose a general approach for personalized text generation using large language models (LLMs). Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation. In writing instruction, the task of writing from sources is often decomposed into multiple steps that involve finding, evaluating, summarizing, synthesizing, and integrating information. Analogously, our approach to personalized text generation consists of multiple stages: retrieval, ranking, summarization, synthesis, and generation. In addition, we introduce a multitask setting that helps the model improve its generation ability further, which is inspired by the observation in education that a student's reading proficiency and writing ability are often correlated. We evaluate our approach on three public datasets, each of which covers a different and representative domain. Our results show significant improvements over a variety of baselines.

From pre-trained language model (PLM) to large language model (LLM), the field of natural language processing (NLP) has witnessed steep performance gains and wide practical uses. The evaluation of a research field guides its direction of improvement. However, LLMs are extremely hard to thoroughly evaluate for two reasons. First of all, traditional NLP tasks become inadequate due to the excellent performance of LLM. Secondly, existing evaluation tasks are difficult to keep up with the wide range of applications in real-world scenarios. To tackle these problems, existing works proposed various benchmarks to better evaluate LLMs. To clarify the numerous evaluation tasks in both academia and industry, we investigate multiple papers concerning LLM evaluations. We summarize 4 core competencies of LLM, including reasoning, knowledge, reliability, and safety. For every competency, we introduce its definition, corresponding benchmarks, and metrics. Under this competency architecture, similar tasks are combined to reflect corresponding ability, while new tasks can also be easily added into the system. Finally, we give our suggestions on the future direction of LLM's evaluation.

Boolean Satisfiability (SAT) and Satisfiability Modulo Theories (SMT) are widely used in automated verification, but there is a lack of interactive tools designed for educational purposes in this field. To address this gap, we present EduSAT, a pedagogical tool specifically developed to support learning and understanding of SAT and SMT solving. EduSAT offers implementations of key algorithms such as the Davis-Putnam-Logemann-Loveland (DPLL) algorithm and the Reduced Order Binary Decision Diagram (ROBDD) for SAT solving. Additionally, EduSAT provides solver abstractions for five NP-complete problems beyond SAT and SMT. Users can benefit from EduSAT by experimenting, analyzing, and validating their understanding of SAT and SMT solving techniques. Our tool is accompanied by comprehensive documentation and tutorials, extensive testing, and practical features such as a natural language interface and SAT and SMT formula generators, which also serve as a valuable opportunity for learners to deepen their understanding. Our evaluation of EduSAT demonstrates its high accuracy, achieving 100% correctness across all the implemented SAT and SMT solvers. We release EduSAT as a python package in .whl file, and the source can be identified at https://github.com/zhaoy37/SAT_Solver.

Artificial intelligence (AI) is rapidly becoming one of the key technologies of this century. The majority of results in AI thus far have been achieved using deep neural networks trained with the error backpropagation learning algorithm. However, the ubiquitous adoption of this approach has highlighted some important limitations such as substantial computational cost, difficulty in quantifying uncertainty, lack of robustness, unreliability, and biological implausibility. It is possible that addressing these limitations may require schemes that are inspired and guided by neuroscience theories. One such theory, called predictive coding (PC), has shown promising performance in machine intelligence tasks, exhibiting exciting properties that make it potentially valuable for the machine learning community: PC can model information processing in different brain areas, can be used in cognitive control and robotics, and has a solid mathematical grounding in variational inference, offering a powerful inversion scheme for a specific class of continuous-state generative models. With the hope of foregrounding research in this direction, we survey the literature that has contributed to this perspective, highlighting the many ways that PC might play a role in the future of machine learning and computational intelligence at large.

Online learning methods yield sequential regret bounds under minimal assumptions and provide in-expectation risk bounds for statistical learning. However, despite the apparent advantage of online guarantees over their statistical counterparts, recent findings indicate that in many important cases, regret bounds may not guarantee tight high-probability risk bounds in the statistical setting. In this work we show that online to batch conversions applied to general online learning algorithms can bypass this limitation. Via a general second-order correction to the loss function defining the regret, we obtain nearly optimal high-probability risk bounds for several classical statistical estimation problems, such as discrete distribution estimation, linear regression, logistic regression, and conditional density estimation. Our analysis relies on the fact that many online learning algorithms are improper, as they are not restricted to use predictors from a given reference class. The improper nature of our estimators enables significant improvements in the dependencies on various problem parameters. Finally, we discuss some computational advantages of our sequential algorithms over their existing batch counterparts.

This paper presents a novel Learning from Demonstration (LfD) method that uses neural fields to learn new skills efficiently and accurately. It achieves this by utilizing a shared embedding to learn both scene and motion representations in a generative way. Our method smoothly maps each expert demonstration to a scene-motion embedding and learns to model them without requiring hand-crafted task parameters or large datasets. It achieves data efficiency by enforcing scene and motion generation to be smooth with respect to changes in the embedding space. At inference time, our method can retrieve scene-motion embeddings using test time optimization, and generate precise motion trajectories for novel scenes. The proposed method is versatile and can employ images, 3D shapes, and any other scene representations that can be modeled using neural fields. Additionally, it can generate both end-effector positions and joint angle-based trajectories. Our method is evaluated on tasks that require accurate motion trajectory generation, where the underlying task parametrization is based on object positions and geometric scene changes. Experimental results demonstrate that the proposed method outperforms the baseline approaches and generalizes to novel scenes. Furthermore, in real-world experiments, we show that our method can successfully model multi-valued trajectories, it is robust to the distractor objects introduced at inference time, and it can generate 6D motions.

Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for delivering a proper answer given the input query. However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i.e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer. This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate the answer. In this paper, we propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach, addressing the above challenge by distilling knowledge from a generative passage estimator (GPE) to a passage ranker, where the GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We realize the distillation procedure by teaching the passage ranker learning to rank the passages ordered by the GPE. Furthermore, we improve the distillation quality by devising a curriculum knowledge distillation mechanism, which allows the knowledge provided by the GPE can be progressively distilled to the ranker through an easy-to-hard curriculum, enabling the passage ranker to correctly recognize the provenance of the answer from many plausible candidates. We conduct extensive experiments on four datasets across three knowledge-intensive language tasks. Experimental results show advantages over the state-of-the-art methods for both passage ranking and answer generation on the KILT benchmark.

We present Self-Driven Strategy Learning ($\textit{sdsl}$), a lightweight online learning methodology for automated reasoning tasks that involve solving a set of related problems. $\textit{sdsl}$ does not require offline training, but instead automatically constructs a dataset while solving earlier problems. It fits a machine learning model to this data which is then used to adjust the solving strategy for later problems. We formally define the approach as a set of abstract transition rules. We describe a concrete instance of the sdsl calculus which uses conditional sampling for generating data and random forests as the underlying machine learning model. We implement the approach on top of the Kissat solver and show that the combination of Kissat+$\textit{sdsl}$ certifies larger bounds and finds more counter-examples than other state-of-the-art bounded model checking approaches on benchmarks obtained from the latest Hardware Model Checking Competition.

It certainly didn't take long for AI's other shoe to drop, what with the emergent technology already being perverted to commit confidence scams and generate spam content. We can now add censorship to that list as the Globe Gazette reports the school board of Mason City, Iowa has begun leveraging AI technology to cultivate lists of potentially bannable books from the district's libraries ahead of the 2023/24 school year. In May, the Republican-controlled state legislature passed, and Governor Kim Reynolds subsequently signed, Senate File 496 (SF 496), which enacted sweeping changes to the state's education curriculum. Specifically it limits what books can be made available in school libraries and classrooms, requiring titles to be "age appropriate" and without "descriptions or visual depictions of a sex act," per Iowa Code 702.17. But ensuring that every book in the district's archives adhere to these new rules is quickly turning into a mammoth undertaking.

AI surveillance might deter cheaters. But sometimes these detectors get it wrong, too. And even a small "false positive" error rate means some students could be wrongly accused -- an experience with potentially devastating long-term effects. After I wrote about the arrival of the AI detector from Turnitin, I heard from many angry high school and college students (and some of their parents) claiming they had been falsely accused of AI cheating. So I asked some of them how they handled the accusations, and I also sought some advice from experts in academic integrity and AI.