Modern Software Engineering era is moving fast with the assistance of artificial intelligence (AI), especially Large Language Models (LLM). Researchers have already started automating many parts of the software development workflow. Requirements Engineering (RE) is a crucial phase that begins the software development cycle through multiple discussions on a proposed scope of work documented in different forms. RE phase ends with a list of user-stories for each unit task identified through discussions and usually these are created and tracked on a project management tool such as Jira, AzurDev etc. In this research we developed a tool "GeneUS" using GPT-4.0 to automatically create user stories from requirements document which is the outcome of the RE phase. The output is provided in JSON format leaving the possibilities open for downstream integration to the popular project management tools. Analyzing requirements documents takes significant effort and multiple meetings with stakeholders. We believe, automating this process will certainly reduce additional load off the software engineers, and increase the productivity since they will be able to utilize their time on other prioritized tasks.

With the digitization of modern cities, large data volumes and powerful computational resources facilitate the rapid update of intelligent models deployed in smart cities. Continual learning (CL) is a novel machine learning paradigm that constantly updates models to adapt to changing environments, where the learning tasks, data, and distributions can vary over time. Our survey provides a comprehensive review of continual learning methods that are widely used in smart city development. The content consists of three parts: 1) Methodology-wise. We categorize a large number of basic CL methods and advanced CL frameworks in combination with other learning paradigms including graph learning, spatial-temporal learning, multi-modal learning, and federated learning. 2) Application-wise. We present numerous CL applications covering transportation, environment, public health, safety, networks, and associated datasets related to urban computing. 3) Challenges. We discuss current problems and challenges and envision several promising research directions. We believe this survey can help relevant researchers quickly familiarize themselves with the current state of continual learning research used in smart city development and direct them to future research trends.

Retrieval-Augmented Generation (RAG) is essential for integrating external knowledge into Large Language Model (LLM) outputs. While the literature on RAG is growing, it primarily focuses on systematic reviews and comparisons of new state-of-the-art (SoTA) techniques against their predecessors, with a gap in extensive experimental comparisons. This study begins to address this gap by assessing various RAG methods' impacts on retrieval precision and answer similarity. We found that Hypothetical Document Embedding (HyDE) and LLM reranking significantly enhance retrieval precision. However, Maximal Marginal Relevance (MMR) and Cohere rerank did not exhibit notable advantages over a baseline Naive RAG system, and Multi-query approaches underperformed. Sentence Window Retrieval emerged as the most effective for retrieval precision, despite its variable performance on answer similarity. The study confirms the potential of the Document Summary Index as a competent retrieval approach. All resources related to this research are publicly accessible for further investigation through our GitHub repository ARAGOG (https://github.com/predlico/ARAGOG). We welcome the community to further this exploratory study in RAG systems.

While long-context large language models (LLMs) can technically summarize book-length documents (>100K tokens), the length and complexity of the documents have so far prohibited evaluations of input-dependent aspects like faithfulness. In this paper, we conduct the first large-scale human evaluation of faithfulness and content selection on LLM-generated summaries of fictional books. Our study mitigates the issue of data contamination by focusing on summaries of books published in 2023 or 2024, and we hire annotators who have fully read each book prior to the annotation task to minimize cost and cognitive burden. We collect FABLES, a dataset of annotations on 3,158 claims made in LLM-generated summaries of 26 books, at a cost of $5.2K USD, which allows us to rank LLM summarizers based on faithfulness: Claude-3-Opus significantly outperforms all closed-source LLMs, while the open-source Mixtral is on par with GPT-3.5-Turbo. An analysis of the annotations reveals that most unfaithful claims relate to events and character states, and they generally require indirect reasoning over the narrative to invalidate. While LLM-based auto-raters have proven reliable for factuality and coherence in other settings, we implement several LLM raters of faithfulness and find that none correlates strongly with human annotations, especially with regard to detecting unfaithful claims. Our experiments suggest that detecting unfaithful claims is an important future direction not only for summarization evaluation but also as a testbed for long-context understanding. Finally, we move beyond faithfulness by exploring content selection errors in book-length summarization: we develop a typology of omission errors related to crucial narrative elements and also identify a systematic over-emphasis on events occurring towards the end of the book.

Large language models (LLMs) have offered new opportunities for emotional support, and recent work has shown that they can produce empathic responses to people in distress. However, long-term mental well-being requires emotional self-regulation, where a one-time empathic response falls short. This work takes a first step by engaging with cognitive reappraisals, a strategy from psychology practitioners that uses language to targetedly change negative appraisals that an individual makes of the situation; such appraisals is known to sit at the root of human emotional experience. We hypothesize that psychologically grounded principles could enable such advanced psychology capabilities in LLMs, and design RESORT which consists of a series of reappraisal constitutions across multiple dimensions that can be used as LLM instructions. We conduct a first-of-its-kind expert evaluation (by clinical psychologists with M.S. or Ph.D. degrees) of an LLM's zero-shot ability to generate cognitive reappraisal responses to medium-length social media messages asking for support. This fine-grained evaluation showed that even LLMs at the 7B scale guided by RESORT are capable of generating empathic responses that can help users reappraise their situations.

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations.

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content) surprisingly leads to substantial degradation in safety. We delve into the data-centric aspects of why benign fine-tuning inadvertently contributes to jailbreaking. First, we represent fine-tuning data through two lenses: representation and gradient spaces. Furthermore, we propose a bi-directional anchoring method that prioritizes data points that are close to harmful examples and distant from benign ones. By doing so, our approach effectively identifies subsets of benign data that are more likely to degrade the model's safety after fine-tuning. Training on just 100 of these seemingly benign datapoints can lead to the fine-tuned model affirmatively responding to > 70% of tested harmful requests, compared to < 20% after fine-tuning on randomly selected data. We further find that selected data are often in the form of lists and bullet points, or math questions.

Large language models (LLMs) have exhibited memorable strategic behaviors in social deductive games. However, the significance of opinion leadership exhibited by LLM-based agents has been overlooked, which is crucial for practical applications in multi-agent and human-AI interaction settings. Opinion leaders are individuals who have a noticeable impact on the beliefs and behaviors of others within a social group. In this work, we employ the Werewolf game as a simulation platform to assess the opinion leadership of LLMs. The game features the role of the Sheriff, tasked with summarizing arguments and recommending decision options, and therefore serves as a credible proxy for an opinion leader. We develop a framework integrating the Sheriff role and devise two novel metrics for evaluation based on the critical characteristics of opinion leaders. The first metric measures the reliability of the opinion leader, and the second assesses the influence of the opinion leader on other players' decisions. We conduct extensive experiments to evaluate LLMs of different scales. In addition, we collect a Werewolf question-answering dataset (WWQA) to assess and enhance LLM's grasp of the game rules, and we also incorporate human participants for further analysis. The results suggest that the Werewolf game is a suitable test bed to evaluate the opinion leadership of LLMs and few LLMs possess the capacity for opinion leadership.

We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency. While improved network architecture and inference algorithms have shown to effectively boost sampling efficiency of diffusion models, the role of model size -- a critical determinant of sampling efficiency -- has not been thoroughly examined. Through empirical analysis of established text-to-image diffusion models, we conduct an in-depth investigation into how model size influences sampling efficiency across varying sampling steps. Our findings unveil a surprising trend: when operating under a given inference budget, smaller models frequently outperform their larger equivalents in generating high-quality results. Moreover, we extend our study to demonstrate the generalizability of the these findings by applying various diffusion samplers, exploring diverse downstream tasks, evaluating post-distilled models, as well as comparing performance relative to training compute. These findings open up new pathways for the development of LDM scaling strategies which can be employed to enhance generative capabilities within limited inference budgets.

In an effort to reduce the computational load of Transformers, research on linear attention has gained significant momentum. However, the improvement strategies for attention mechanisms typically necessitate extensive retraining, which is impractical for large language models with a vast array of parameters. In this paper, we present DiJiang, a novel Frequency Domain Kernelization approach that enables the transformation of a pre-trained vanilla Transformer into a linear complexity model with little training costs. By employing a weighted Quasi-Monte Carlo method for sampling, the proposed approach theoretically offers superior approximation efficiency. To further reduce the training computational complexity, our kernelization is based on Discrete Cosine Transform (DCT) operations. Extensive experiments demonstrate that the proposed method achieves comparable performance to the original Transformer, but with significantly reduced training costs and much faster inference speeds. Our DiJiang-7B achieves comparable performance with LLaMA2-7B on various benchmark while requires only about 1/50 training cost. Code is available at https://github.com/YuchuanTian/DiJiang.