Recently, it has been recognized that large language models demonstrate high performance on various intellectual tasks. However, few studies have investigated alignment with humans in behaviors that involve sensibility, such as aesthetic evaluation. This study investigates the performance of GPT-4 with Vision, a state-of-the-art language model that can handle image input, on the task of aesthetic evaluation of images. We employ two tasks, prediction of the average evaluation values of a group and an individual's evaluation values. We investigate the performance of GPT-4 with Vision by exploring prompts and analyzing prediction behaviors. Experimental results reveal GPT-4 with Vision's superior performance in predicting aesthetic evaluations and the nature of different responses to beauty and ugliness. Finally, we discuss developing an AI system for aesthetic evaluation based on scientific knowledge of the human perception of beauty, employing agent technologies that integrate traditional deep learning models with large language models.

Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. However, most LLMs today, and open LLMs in particular, are often intended for use in just English (e.g. Llama2, Mistral) or a small handful of high-resource languages (e.g. Mixtral, Qwen). Recent research shows that, despite limits in their intended use, people prompt LLMs in many different languages. Therefore, in this paper, we investigate the basic multilingual capabilities of state-of-the-art open LLMs beyond their intended use. For this purpose, we introduce MultiQ, a new silver standard benchmark for basic open-ended question answering with 27.4k test questions across a typologically diverse set of 137 languages. With MultiQ, we evaluate language fidelity, i.e.\ whether models respond in the prompted language, and question answering accuracy. All LLMs we test respond faithfully and/or accurately for at least some languages beyond their intended use. Most models are more accurate when they respond faithfully. However, differences across models are large, and there is a long tail of languages where models are neither accurate nor faithful. We explore differences in tokenization as a potential explanation for our findings, identifying possible correlations that warrant further investigation.

The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy risks at the cost of generalization degradation. Our paper reveals that the flatness of DP-trained models' loss landscape plays an essential role in the trade-off between their privacy and generalization. We further propose a holistic framework to enforce appropriate weight flatness, which substantially improves model generalization with competitive privacy preservation. It innovates from three coarse-to-grained levels, including perturbation-aware min-max optimization on model weights within a layer, flatness-guided sparse prefix-tuning on weights across layers, and weight knowledge distillation between DP \& non-DP weights copies. Comprehensive experiments of both black-box and white-box scenarios are conducted to demonstrate the effectiveness of our proposal in enhancing generalization and maintaining DP characteristics. For instance, on text classification dataset QNLI, DP-Flat achieves similar performance with non-private full fine-tuning but with DP guarantee under privacy budget $\epsilon=3$, and even better performance given higher privacy budgets. Codes are provided in the supplement.

The growing complexity of cloud based software systems has resulted in incident management becoming an integral part of the software development lifecycle. Root cause analysis (RCA), a critical part of the incident management process, is a demanding task for on-call engineers, requiring deep domain knowledge and extensive experience with a team's specific services. Automation of RCA can result in significant savings of time, and ease the burden of incident management on on-call engineers. Recently, researchers have utilized Large Language Models (LLMs) to perform RCA, and have demonstrated promising results. However, these approaches are not able to dynamically collect additional diagnostic information such as incident related logs, metrics or databases, severely restricting their ability to diagnose root causes. In this work, we explore the use of LLM based agents for RCA to address this limitation. We present a thorough empirical evaluation of a ReAct agent equipped with retrieval tools, on an out-of-distribution dataset of production incidents collected at Microsoft. Results show that ReAct performs competitively with strong retrieval and reasoning baselines, but with highly increased factual accuracy. We then extend this evaluation by incorporating discussions associated with incident reports as additional inputs for the models, which surprisingly does not yield significant performance improvements. Lastly, we conduct a case study with a team at Microsoft to equip the ReAct agent with tools that give it access to external diagnostic services that are used by the team for manual RCA. Our results show how agents can overcome the limitations of prior work, and practical considerations for implementing such a system in practice.

The Vehicle Routing Problem (VRP) is a widely studied combinatorial optimization problem and has been applied to various practical problems. While the explainability for VRP is significant for improving the reliability and interactivity in practical VRP applications, it remains unexplored. In this paper, we propose RouteExplainer, a post-hoc explanation framework that explains the influence of each edge in a generated route. Our framework realizes this by rethinking a route as the sequence of actions and extending counterfactual explanations based on the action influence model to VRP. To enhance the explanation, we additionally propose an edge classifier that infers the intentions of each edge, a loss function to train the edge classifier, and explanation-text generation by Large Language Models (LLMs). We quantitatively evaluate our edge classifier on four different VRPs. The results demonstrate its rapid computation while maintaining reasonable accuracy, thereby highlighting its potential for deployment in practical applications. Moreover, on the subject of a tourist route, we qualitatively evaluate explanations generated by our framework. This evaluation not only validates our framework but also shows the synergy between explanation frameworks and LLMs.

Text documents, including programs, typically have human-readable semantic structure. Historically, programmatic access to these semantics has required explicit in-document tagging. Especially in systems where the text has an execution semantics, this means it is an opt-in feature that is hard to support properly. Today, language models offer a new method: metadata can be bound to entities in changing text using a model's human-like understanding of semantics, with no requirements on the document structure. This method expands the applications of document annotation, a fundamental operation in program writing, debugging, maintenance, and presentation. We contribute a system that employs an intelligent agent to re-tag modified programs, enabling rich annotations to automatically follow code as it evolves. We also contribute a formal problem definition, an empirical synthetic benchmark suite, and our benchmark generator. Our system achieves an accuracy of 90% on our benchmarks and can replace a document's tags in parallel at a rate of 5 seconds per tag. While there remains significant room for improvement, we find performance reliable enough to justify further exploration of applications.

Many online content portals allow users to ask questions to supplement their understanding (e.g., of lectures). While information retrieval (IR) systems may provide answers for such user queries, they do not directly assist content creators -- such as lecturers who want to improve their content -- identify segments that _caused_ a user to ask those questions. We introduce the task of backtracing, in which systems retrieve the text segment that most likely caused a user query. We formalize three real-world domains for which backtracing is important in improving content delivery and communication: understanding the cause of (a) student confusion in the Lecture domain, (b) reader curiosity in the News Article domain, and (c) user emotion in the Conversation domain. We evaluate the zero-shot performance of popular information retrieval methods and language modeling methods, including bi-encoder, re-ranking and likelihood-based methods and ChatGPT. While traditional IR systems retrieve semantically relevant information (e.g., details on "projection matrices" for a query "does projecting multiple times still lead to the same point?"), they often miss the causally relevant context (e.g., the lecturer states "projecting twice gets me the same answer as one projection"). Our results show that there is room for improvement on backtracing and it requires new retrieval approaches. We hope our benchmark serves to improve future retrieval systems for backtracing, spawning systems that refine content generation and identify linguistic triggers influencing user queries. Our code and data are open-sourced: https://github.com/rosewang2008/backtracing.

The growing dependence on Large Language Models (LLMs) for finishing user instructions necessitates a comprehensive understanding of their robustness to complex task completion in real-world situations. To address this critical need, we propose the PowerPoint Task Completion Robustness benchmark (PPTC-R) to measure LLMs' robustness to the user PPT task instruction and software version. Specifically, we construct adversarial user instructions by attacking user instructions at sentence, semantic, and multi-language levels. To assess the robustness of Language Models to software versions, we vary the number of provided APIs to simulate both the newest version and earlier version settings. Subsequently, we test 3 closed-source and 4 open-source LLMs using a benchmark that incorporates these robustness settings, aiming to evaluate how deviations impact LLMs' API calls for task completion. We find that GPT-4 exhibits the highest performance and strong robustness in our benchmark, particularly in the version update and the multilingual settings. However, we find that all LLMs lose their robustness when confronted with multiple challenges (e.g., multi-turn) simultaneously, leading to significant performance drops. We further analyze the robustness behavior and error reasons of LLMs in our benchmark, which provide valuable insights for researchers to understand the LLM's robustness in task completion and develop more robust LLMs and agents. We release the code and data at \url{https://github.com/ZekaiGalaxy/PPTCR}.

Large Language Models (LLMs) have unlocked new capabilities and applications; however, evaluating the alignment with human preferences still poses significant challenges. To address this issue, we introduce Chatbot Arena, an open platform for evaluating LLMs based on human preferences. Our methodology employs a pairwise comparison approach and leverages input from a diverse user base through crowdsourcing. The platform has been operational for several months, amassing over 240K votes. This paper describes the platform, analyzes the data we have collected so far, and explains the tried-and-true statistical methods we are using for efficient and accurate evaluation and ranking of models. We confirm that the crowdsourced questions are sufficiently diverse and discriminating and that the crowdsourced human votes are in good agreement with those of expert raters. These analyses collectively establish a robust foundation for the credibility of Chatbot Arena. Because of its unique value and openness, Chatbot Arena has emerged as one of the most referenced LLM leaderboards, widely cited by leading LLM developers and companies. Our demo is publicly available at \url{https://chat.lmsys.org}.

This study investigates the generation of synthetic disinformation by OpenAI's Large Language Models (LLMs) through prompt engineering and explores their responsiveness to emotional prompting. Leveraging various LLM iterations using davinci-002, davinci-003, gpt-3.5-turbo and gpt-4, we designed experiments to assess their success in producing disinformation. Our findings, based on a corpus of 19,800 synthetic disinformation social media posts, reveal that all LLMs by OpenAI can successfully produce disinformation, and that they effectively respond to emotional prompting, indicating their nuanced understanding of emotional cues in text generation. When prompted politely, all examined LLMs consistently generate disinformation at a high frequency. Conversely, when prompted impolitely, the frequency of disinformation production diminishes, as the models often refuse to generate disinformation and instead caution users that the tool is not intended for such purposes. This research contributes to the ongoing discourse surrounding responsible development and application of AI technologies, particularly in mitigating the spread of disinformation and promoting transparency in AI-generated content.