We present an empirical study of groundedness in long-form question answering (LFQA) by retrieval-augmented large language models (LLMs). In particular, we evaluate whether every generated sentence is grounded in the retrieved documents or the model's pre-training data. Across 3 datasets and 4 model families, our findings reveal that a significant fraction of generated sentences are consistently ungrounded, even when those sentences contain correct ground-truth answers. Additionally, we examine the impacts of factors such as model size, decoding strategy, and instruction tuning on groundedness. Our results show that while larger models tend to ground their outputs more effectively, a significant portion of correct answers remains compromised by hallucinations. This study provides novel insights into the groundedness challenges in LFQA and underscores the necessity for more robust mechanisms in LLMs to mitigate the generation of ungrounded content.

In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible with ABC Notation, which aligns more closely with their design and strengths, thereby enhancing the model's performance in musical composition. To address the challenges associated with misaligned measures from different tracks during generation, we propose the development of a Synchronized Multi-Track ABC Notation (SMT-ABC Notation), which aims to preserve coherence across multiple musical tracks. Our contributions include a series of models capable of handling up to 8192 tokens, covering 90% of the symbolic music data in our training set. Furthermore, we explore the implications of the Symbolic Music Scaling Law (SMS Law) on model performance. The results indicate a promising direction for future research in music generation, offering extensive resources for community-led research through our open-source contributions.

Portfolio management is one of the unresponded problems of the Motion Pictures Industry (MPI). To design an optimal portfolio for an MPI distributor, it is essential to predict the box office of each project. Moreover, for an accurate box office prediction, it is critical to consider the effect of the celebrities involved in each MPI project, which was impossible with any precedent expert-based method. Additionally, the asymmetric characteristic of MPI data decreases the performance of any predictive algorithm. In this paper, firstly, the fame score of the celebrities is determined using a large language model. Then, to tackle the asymmetric character of MPI's data, projects are classified. Furthermore, the box office prediction takes place for each class of projects. Finally, using a hybrid multi-attribute decision-making technique, the preferability of each project for the distributor is calculated, and benefiting from a bi-objective optimization model, the optimal portfolio is designed.

The bill would need companies to file such documents at least 30 days before publicly debuting their AI tools, or face a financial penalty. Such datasets encompass billions of lines of text and images or millions of hours of music and movies. "AI has the disruptive potential of changing our economy, our political system, and our day-to-day lives. We must balance the immense potential of AI with the crucial need for ethical guidelines and protections," Schiff said in a statement. Schiff's bill, which was first reported by Billboard, has received the support of numerous entertainment industry organizations and unions, including the Recording Industry Association of America, Professional Photographers of America, Directors Guild of America and the Screen Actors Guild-American Federation of Television and Radio Artists.

'The Five' co-hosts discuss how Bill Maher is blasting the left's obsession with race. "Star Wars" actor Billy Dee Williams pushed back on Bill Maher's "Club Random" podcast after the liberal host called today's youth "fragile." The two commiserated over not understanding the younger generations before Maher launched into a blistering tirade against today's youth. The liberal host called modern young adults "fragile" like "hothouse plants," because they were "raised wrong." Williams, who played Lando Calrissian in Star Wars, offered, before suggesting the younger generations simply lacked a "sense of history."

Text-to-video generative AI models such as Sora OpenAI have the potential to disrupt multiple industries. In this paper, we report a qualitative social media analysis aiming to uncover people's perceived impact of and concerns about Sora's integration. We collected and analyzed comments (N=292) under popular posts about Sora-generated videos, comparison between Sora videos and Midjourney images, and artists' complaints about copyright infringement by Generative AI. We found that people were most concerned about Sora's impact on content creation-related industries. Emerging governance challenges included the for-profit nature of OpenAI, the blurred boundaries between real and fake content, human autonomy, data privacy, copyright issues, and environmental impact. Potential regulatory solutions proposed by people included law-enforced labeling of AI content and AI literacy education for the public. Based on the findings, we discuss the importance of gauging people's tech perceptions early and propose policy recommendations to regulate Sora before its public release.

The emergence of Large Language Models (LLMs) has innovated the development of dialog agents. Specially, a well-trained LLM, as a central process unit, is capable of providing fluent and reasonable response for user's request. Besides, auxiliary tools such as external knowledge retrieval, personalized character for vivid response, short/long-term memory for ultra long context management are developed, completing the usage experience for LLM-based dialog agents. However, the above-mentioned techniques does not solve the issue of \textbf{personalization from user perspective}: agents response in a same fashion to different users, without consideration of their features, such as habits, interests and past experience. In another words, current implementation of dialog agents fail in ``knowing the user''. The capacity of well-description and representation of user is under development. In this work, we proposed a framework for dialog agent to incorporate user profiling (initialization, update): user's query and response is analyzed and organized into a structural user profile, which is latter served to provide personal and more precise response. Besides, we proposed a series of evaluation protocols for personalization: to what extend the response is personal to the different users. The framework is named as \method{}, inspired by inscription of ``Know Yourself'' in the temple of Apollo (also known as \method{}) in Ancient Greek. Few works have been conducted on incorporating personalization into LLM, \method{} is a pioneer work on guiding LLM's response to meet individuation via the application of dialog agents, with a set of evaluation methods for measurement in personalization.

Recently a lot of progress has been made in rumor modeling and rumor detection for micro-blogging streams. However, existing automated methods do not perform very well for early rumor detection, which is crucial in many settings, e.g., in crisis situations. One reason for this is that aggregated rumor features such as propagation features, which work well on the long run, are - due to their accumulating characteristic - not very helpful in the early phase of a rumor. In this work, we present an approach for early rumor detection, which leverages Convolutional Neural Networks for learning the hidden representations of individual rumor-related tweets to gain insights on the credibility of each tweets. We then aggregate the predictions from the very beginning of a rumor to obtain the overall event credits (so-called wisdom), and finally combine it with a time series based rumor classification model. Our extensive experiments show a clearly improved classification performance within the critical very first hours of a rumor. For a better understanding, we also conduct an extensive feature evaluation that emphasized on the early stage and shows that the low-level credibility has best predictability at all phases of the rumor lifetime.

Best practices for high conflict conversations like counseling or customer support almost always include recommendations to paraphrase the previous speaker. Although paraphrase classification has received widespread attention in NLP, paraphrases are usually considered independent from context, and common models and datasets are not applicable to dialog settings. In this work, we investigate paraphrases in dialog (e.g., Speaker 1: "That book is mine." becomes Speaker 2: "That book is yours."). We provide an operationalization of context-dependent paraphrases, and develop a training for crowd-workers to classify paraphrases in dialog. We introduce a dataset with utterance pairs from NPR and CNN news interviews annotated for context-dependent paraphrases. To enable analyses on label variation, the dataset contains 5,581 annotations on 600 utterance pairs. We present promising results with in-context learning and with token classification models for automatic paraphrase detection in dialog.

This paper addresses debiasing in news editing and evaluates the effectiveness of conversational Large Language Models in this task. We designed an evaluation checklist tailored to news editors' perspectives, obtained generated texts from three popular conversational models using a subset of a publicly available dataset in media bias, and evaluated the texts according to the designed checklist. Furthermore, we examined the models as evaluator for checking the quality of debiased model outputs. Our findings indicate that none of the LLMs are perfect in debiasing. Notably, some models, including ChatGPT, introduced unnecessary changes that may impact the author's style and create misinformation. Lastly, we show that the models do not perform as proficiently as domain experts in evaluating the quality of debiased outputs.