This paper presents H4MF model (HMM MF for dynamic Missingness) for implicit feedback data. With implicit data, we only observe positive feedback and the missing entries (zeros) in the data can indicate either negative feedback or users are not exposed of the items. H4MF is based on the previous work on modeling user latent exposure (ExpoMF, Liang et al., Modeling user exposure in recommendation, 2016) -- the basic idea is that for each user-item pair, there is a latent binary variable to represent exposure; if it's 1, it means this user is exposed to the item thus 0 feedback mean true negative, while if it's 0, it means this user have not yet been exposed to this item yet. The difference in H4MF is that H4MF uses a hidden Markov model to capture the temporal dynamics in the user exposure (user intent in this paper). The basic idea is that whether or not a user is exposed to something can be dependent on some other items he/she has been exposed before.

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences. To enable this ability for instruction-tuned large language models (LLMs), one may prompt them to ask users questions to infer their preferences, transforming the language models into more robust, interactive systems. However, out of the box, these models are not efficient at extracting preferences: the questions they generate are not informative, requiring a high number of user interactions and impeding the usability of the downstream system. In this work, we introduce an inference-time algorithm that helps LLMs quickly infer preferences by using more informative questions. Our algorithm uses a probabilistic model whose conditional distributions are defined by prompting an LLM, and returns questions that optimize expected entropy and expected model change. Results in a simplified interactive web shopping setting with real product items show that an LLM equipped with our entropy reduction algorithm outperforms baselines with the same underlying LLM on task performance while using fewer user interactions.

The conversational machine reading comprehension (CMRC) task aims to answer questions in conversations, which has been a hot research topic in recent years because of its wide applications. However, existing CMRC benchmarks in which each conversation is assigned a static passage are inconsistent with real scenarios. Thus, model's comprehension ability towards real scenarios are hard to evaluate reasonably. To this end, we propose the first Chinese CMRC benchmark Orca and further provide zero-shot/few-shot settings to evaluate model's generalization ability towards diverse domains. We collect 831 hot-topic driven conversations with 4,742 turns in total. Each turn of a conversation is assigned with a response-related passage, aiming to evaluate model's comprehension ability more reasonably. The topics of conversations are collected from social media platform and cover 33 domains, trying to be consistent with real scenarios. Importantly, answers in Orca are all well-annotated natural responses rather than the specific spans or short phrase in previous datasets. Besides, we implement three strong baselines to tackle the challenge in Orca. The results indicate the great challenge of our CMRC benchmark. Our datatset and checkpoints are available at https://github.com/nuochenpku/Orca.

Save on the things that will make the school year easier. If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. There are few things in life that get me excited in the middle of the workweek--and one of those things is a good deal. The kind of deal that's so good on a product you've been eyeing for a while that it makes you want to shout about it from the rooftop.

The color-changing capabilities of chameleons have long bewildered willing observers. The philosopher Aristotle himself was long mystified by these adaptive creatures. But while humans can't yet camouflage much beyond a green outfit to match grass, inanimate objects are another story. A team from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) has brought us closer to this chameleon reality, by way of a new system that uses reprogrammable ink to let objects change colors when exposed to ultraviolet (UV) and visible light sources. Dubbed "PhotoChromeleon," the system uses a mix of photochromic dyes that can be sprayed or painted onto the surface of any object to change its color -- a fully reversible process that can be repeated infinitely.

Imagine you and a group of friends are at the peak of a mountain after a long hike. It's sunset and the sky is alight; you want to take a photo. You pull out your smartphone, but instead of flipping it around to take a long-armed selfie, you unclip a tiny drone from the back of your phone, make it hover at the perfect height, and snap a series of photos, no extendo-arms required. That's the idea behind Selfly, the drone-in-a-phone-case built by camera and recording company AEE. Selfly is a drone that folds into the back of a phone case, and it includes a camera that can record, live stream and take photos in 1080p and 60fps, using a suite of Sony sensors.