We introduce Affective Visual Dialog, an emotion explanation and reasoning task as a testbed for research on understanding the formation of emotions in visually grounded conversations. The task involves three skills: (1) Dialog-based Question Answering (2) Dialog-based Emotion Prediction and (3) Affective emotion explanation generation based on the dialog. Our key contribution is the collection of a large-scale dataset, dubbed AffectVisDial, consisting of 50K 10-turn visually grounded dialogs as well as concluding emotion attributions and dialog-informed textual emotion explanations, resulting in a total of 27,180 working hours. We explain our design decisions in collecting the dataset and introduce the questioner and answerer tasks that are associated with the participants in the conversation. We train and demonstrate solid Affective Visual Dialog baselines adapted from state-of-the-art models. Remarkably, the responses generated by our models show promising emotional reasoning abilities in response to visually grounded conversations. Our project page is available at https://affective-visual-dialog.github.io.

We introduce Infinitia, a simulation game system that uses generative image and language models at play time to reshape all aspects of the setting and NPCs based on a short description from the player, in a way similar to how settings are created on the fictional Holodeck. Building off the ideas of the Generative Agents paper, our system introduces gameplay elements, such as infinite generated fantasy worlds, controllability of NPC behavior, humorous dialogue, cost & time efficiency, collaboration between players and elements of non-determinism among in-game events. Infinitia is implemented in the Unity engine with a server-client architecture, facilitating the addition of exciting features by community developers in the future. Furthermore, it uses a multiplayer framework to allow humans to be present and interact in the simulation. The simulation will be available in open-alpha shortly at https://infinitia.ai/ and we are looking forward to building upon it with the community.

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a systematic literature review on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We collect and analyze 229 research papers from 2017 to 2023 to answer four key research questions (RQs). In RQ1, we categorize different LLMs that have been employed in SE tasks, characterizing their distinctive features and uses. In RQ2, we analyze the methods used in data collection, preprocessing, and application highlighting the role of well-curated datasets for successful LLM for SE implementation. RQ3 investigates the strategies employed to optimize and evaluate the performance of LLMs in SE. Finally, RQ4 examines the specific SE tasks where LLMs have shown success to date, illustrating their practical contributions to the field. From the answers to these RQs, we discuss the current state-of-the-art and trends, identifying gaps in existing research, and flagging promising areas for future study.

While code-mixing is a common linguistic practice in many parts of the world, collecting high-quality and low-cost code-mixed data remains a challenge for natural language processing (NLP) research. The recent proliferation of Large Language Models (LLMs) compels one to ask: how capable are these systems in generating code-mixed data? In this paper, we explore prompting multilingual LLMs in a zero-shot manner to generate code-mixed data for seven languages in South East Asia (SEA), namely Indonesian, Malay, Chinese, Tagalog, Vietnamese, Tamil, and Singlish. We find that publicly available multilingual instruction-tuned models such as BLOOMZ and Flan-T5-XXL are incapable of producing texts with phrases or clauses from different languages. ChatGPT exhibits inconsistent capabilities in generating code-mixed texts, wherein its performance varies depending on the prompt template and language pairing. For instance, ChatGPT generates fluent and natural Singlish texts (an English-based creole spoken in Singapore), but for English-Tamil language pair, the system mostly produces grammatically incorrect or semantically meaningless utterances. Furthermore, it may erroneously introduce languages not specified in the prompt. Based on our investigation, existing multilingual LLMs exhibit a wide range of proficiency in code-mixed data generation for SEA languages. As such, we advise against using LLMs in this context without extensive human checks.

Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively studying their correctness (independent of the final answer) is difficult without reliable methods for automatic evaluation. We simply do not know how often the stated reasoning steps actually support the final end task predictions. In this work, we present ROSCOE, a suite of interpretable, unsupervised automatic scores that improve and extend previous text generation evaluation metrics. To evaluate ROSCOE against baseline metrics, we design a typology of reasoning errors and collect synthetic and human evaluation scores on commonly used reasoning datasets. In contrast with existing metrics, ROSCOE can measure semantic consistency, logicality, informativeness, fluency, and factuality - among other traits - by leveraging properties of step-by-step rationales. We empirically verify the strength of our metrics on five human annotated and six programmatically perturbed diagnostics datasets - covering a diverse set of tasks that require reasoning skills and show that ROSCOE can consistently outperform baseline metrics.

A computer that uses heat instead of electricity could run algorithms that power neural networks and artificial intelligence – and tamp down their energy budgets. "We have things like ChatGPT which can learn very complicated things about language, but it consumes an amount of energy that is absolutely crazy," says Nicolas Brunner at the University of Geneva in Switzerland. Some estimates put ChatGPT's daily energy consumption on par with more than 30,000 households in the US.

Earlier this month, Sundar Pichai was struggling to write a letter to Alphabet's 180,000 employees. The 51-year-old CEO wanted to laud Google on its 25th birthday, which could have been easy enough. Alphabet's stock market value was around $1.7 trillion. Its vast cloud-computing operation had turned its first profit. Its self-driving cars were ferrying people around San Francisco. And then there was the usual stuff--Google Search still dominated the field, as it had for every minute of this century.

'I had to watch every frame of a recent stabbing video … It will never leave me," says Harun*, one of many moderators reviewing harmful online content in India, as social media companies increasingly move the challenging work offshore. Moderators working in Hyderabad, a major IT hub in south Asia, have spoken of the strain on their mental health of reviewing images and videos of sexual and violent content, sometimes including trafficked children. Many social media platforms in the UK, European Union and US have moved the work to countries such as India and the Philippines. While OpenAI, creator of ChatGPT, has said artificial intelligence could be used to speed up content moderation, it is not expected to end the need for the thousands of human moderators employed by social media platforms. Content moderators in Hyderabad say the work has left them emotionally distressed, depressed and struggling to sleep. "I had to watch every frame of a recent stabbing video of a girl.

As robots acquire increasingly sophisticated skills and see increasingly complex and varied environments, the threat of an edge case or anomalous failure is ever present. For example, Tesla cars have seen interesting failure modes ranging from autopilot disengagements due to inactive traffic lights carried by trucks to phantom braking caused by images of stop signs on roadside billboards. These system-level failures are not due to failures of any individual component of the autonomy stack but rather system-level deficiencies in semantic reasoning. Such edge cases, which we call semantic anomalies, are simple for a human to disentangle yet require insightful reasoning. To this end, we study the application of large language models (LLMs), endowed with broad contextual understanding and reasoning capabilities, to recognize such edge cases and introduce a monitoring framework for semantic anomaly detection in vision-based policies. Our experiments apply this framework to a finite state machine policy for autonomous driving and a learned policy for object manipulation. These experiments demonstrate that the LLM-based monitor can effectively identify semantic anomalies in a manner that shows agreement with human reasoning. Finally, we provide an extended discussion on the strengths and weaknesses of this approach and motivate a research outlook on how we can further use foundation models for semantic anomaly detection.

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum, when in reality, ML models are part of larger systems that include components for training data filtering, output monitoring, and more. In this work, we introduce privacy side channels: attacks that exploit these system-level components to extract private information at far higher rates than is otherwise possible for standalone models. We propose four categories of side channels that span the entire ML lifecycle (training data filtering, input preprocessing, output post-processing, and query filtering) and allow for either enhanced membership inference attacks or even novel threats such as extracting users' test queries. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. Moreover, we show that systems which block language models from regenerating training data can be exploited to allow exact reconstruction of private keys contained in the training set -- even if the model did not memorize these keys. Taken together, our results demonstrate the need for a holistic, end-to-end privacy analysis of machine learning.