Nowadays, neural text generation has made tremendous progress in abstractive summarization tasks. However, most of the existing summarization models take in the whole document all at once, which sometimes cannot meet the needs in practice. Practically, social text streams such as news events and tweets keep growing from time to time, and can only be fed to the summarization system step by step. Hence, in this paper, we propose the task of Stepwise Summarization, which aims to generate a new appended summary each time a new document is proposed. The appended summary should not only summarize the newly added content but also be coherent with the previous summary, to form an up-to-date complete summary. To tackle this challenge, we design an adversarial learning model, named Stepwise Summary Generator (SSG). First, SSG selectively processes the new document under the guidance of the previous summary, obtaining polished document representation. Next, SSG generates the summary considering both the previous summary and the document. Finally, a convolutional-based discriminator is employed to determine whether the newly generated summary is coherent with the previous summary. For the experiment, we extend the traditional two-step update summarization setting to a multi-step stepwise setting, and re-propose a large-scale stepwise summarization dataset based on a public story generation dataset. Extensive experiments on this dataset show that SSG achieves state-of-the-art performance in terms of both automatic metrics and human evaluations. Ablation studies demonstrate the effectiveness of each module in our framework. We also discuss the benefits and limitations of recent large language models on this task.

In the real world, knowledge is constantly evolving, which can render existing knowledge-based datasets outdated. This unreliability highlights the critical need for continuous updates to ensure both accuracy and relevance in knowledge-intensive tasks. To address this, we propose GrowOVER-QA and GrowOVER-Dialogue, dynamic open-domain QA and dialogue benchmarks that undergo a continuous cycle of updates, keeping pace with the rapid evolution of knowledge. Our research indicates that retrieval-augmented language models (RaLMs) struggle with knowledge that has not been trained on or recently updated. Consequently, we introduce a novel retrieval-interactive language model framework, where the language model evaluates and reflects on its answers for further re-retrieval. Our exhaustive experiments demonstrate that our training-free framework significantly improves upon existing methods, performing comparably to or even surpassing continuously trained language models.

Detecting subjectivity in news sentences is crucial for identifying media bias, enhancing credibility, and combating misinformation by flagging opinion-based content. It provides insights into public sentiment, empowers readers to make informed decisions, and encourages critical thinking. While research has developed methods and systems for this purpose, most efforts have focused on English and other high-resourced languages. In this study, we present the first large dataset for subjectivity detection in Arabic, consisting of ~3.6K manually annotated sentences, and GPT-4o based explanation. In addition, we included instructions (both in English and Arabic) to facilitate LLM based fine-tuning. We provide an in-depth analysis of the dataset, annotation process, and extensive benchmark results, including PLMs and LLMs. Our analysis of the annotation process highlights that annotators were strongly influenced by their political, cultural, and religious backgrounds, especially at the beginning of the annotation process. The experimental results suggest that LLMs with in-context learning provide better performance. We aim to release the dataset and resources for the community.

The rapid development and reduced barriers to entry for Text-to-Image (T2I) models have raised concerns about the biases in their outputs, but existing research lacks a holistic definition and evaluation framework of biases, limiting the enhancement of debiasing techniques. To address this issue, we introduce FAIntbench, a holistic and precise benchmark for biases in T2I models. In contrast to existing benchmarks that evaluate bias in limited aspects, FAIntbench evaluate biases from four dimensions: manifestation of bias, visibility of bias, acquired attributes, and protected attributes. We applied FAIntbench to evaluate seven recent large-scale T2I models and conducted human evaluation, whose results demonstrated the effectiveness of FAIntbench in identifying various biases. Our study also revealed new research questions about biases, including the side-effect of distillation. The findings presented here are preliminary, highlighting the potential of FAIntbench to advance future research aimed at mitigating the biases in T2I models. Our benchmark is publicly available to ensure the reproducibility.

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, they have been shown to suffer from a critical limitation pertinent to 'hallucination' in their output. Recent research has focused on investigating and addressing this problem for a variety of tasks such as biography generation, question answering, abstractive summarization, and dialogue generation. However, the crucial aspect pertaining to 'negation' has remained considerably underexplored. Negation is important because it adds depth and nuance to the understanding of language and is also crucial for logical reasoning and inference. In this work, we address the above limitation and particularly focus on studying the impact of negation in LLM hallucinations. Specifically, we study four tasks with negation: 'false premise completion', 'constrained fact generation', 'multiple choice question answering', and 'fact generation'. We show that open-source state-of-the-art LLMs such as LLaMA-2-chat, Vicuna, and Orca-2 hallucinate considerably on all these tasks involving negation which underlines a critical shortcoming of these models. Addressing this problem, we further study numerous strategies to mitigate these hallucinations and demonstrate their impact.

Conversational recommender system is an emerging area that has garnered an increasing interest in the community, especially with the advancements in large language models (LLMs) that enable diverse reasoning over conversational input. Despite the progress, the field has many aspects left to explore. The currently available public datasets for conversational recommendation lack specific user preferences and explanations for recommendations, hindering high-quality recommendations. To address such challenges, we present a novel conversational recommendation dataset named PEARL, synthesized with persona- and knowledge-augmented LLM simulators. We obtain detailed persona and knowledge from real-world reviews and construct a large-scale dataset with over 57k dialogues. Our experimental results demonstrate that utterances in PEARL include more specific user preferences, show expertise in the target domain, and provide recommendations more relevant to the dialogue context than those in prior datasets.

Tech evangelists like to say that AI will eat the world--a reference to a famous line about software from the venture capitalist Marc Andreessen. In the past few weeks, we've finally gotten a sense of what they mean. This spring, tech companies have made clear that AI will be a defining feature of online life, whether people want it to be or not. First, Meta surprised users with an AI chatbot that lives in the search bar on Instagram and Facebook. It has since informed European users that their data are being used to train its AI--presumably sent only to comply with the continent's privacy laws. OpenAI released GPT-4o, billed as a new, more powerful and conversational version of its large language model.

The classic movie 12 Angry Men is titled as such because, well, it's about a jury comprised of 12 men. But viewers have noticed recently that the image Amazon uses for the movie has more than 12 characters in it. Further, their melting, inhuman faces look like they could be somebody's sleep paralysis monsters. The terrifying quality to the characters' faces is just one of the elements indicating the use of AI to generate the image. Their deformed and claw-like hands are another, along with the other obvious AI artifacts in the photo.

We're gearing up to cover Apple's Worldwide Developers Conference (WWDC) next week! In this episode, Cherlynn and Devindra dive into everything they expect at WWDC: Tons of AI announcements; more on iOS 18, iPadOS 18, and macOS 15; and hopefully some improvements for Vision Pro and visionOS. In addition, we chat about what we expect to see at Summer Game Fest and demonstrate how we used an AI editing tool to clear up some awful podcast audio. Devindra also talks with Justin Samuels, the founder of Render ATL, about why he started a massive tech conference in Atlanta. Listen below or subscribe on your podcast app of choice. If you've got suggestions or topics you'd like covered on the show, be sure to email us or drop a note in the comments! And be sure to check out our other podcast, Engadget News! Humane AI warns users its battery case "may pose a fire risk" – 34:36 Welcome back to the Engadget podcast. This week we are getting ready for WWDC 2024 happening in a couple of days.

As if he didn't have enough to deal with amid his beef with Kendrick Lamar (or perhaps to distract from it), Drake showed up on a remix of parody rapper Snowd4y's cover of Plain White T's "Hey There Delilah," called "Wah Gwan Delilah," that has everyone … perplexed? Let's walk through this together, it's a mess. It had what appeared to be Drake joining the comedian in a series of quips about women and name-checks of Toronto landmarks like the Yonge-Dundas Square mall. As the track spread, it made its way to the Plain White T's themselves, who posted a video on X and TikTok with the caption "too stunned to speak." Frontman Tom Higgenson also says "it's crazy that everybody thinks that it's real," seemingly referencing early rumors that Drake's lyrics were generated using artificial intelligence.