As Large Language Models (LLMs) achieve remarkable performance across various NLP tasks, their reliability becomes essential for widespread adoption. This paper focuses on Abstention Ability (AA), a critical yet under explored aspect of reliability - the ability of LLMs to refrain from answering questions when they are uncertain or when definitive answer is not possible, while maintaining question-answering (QA) task performance. While previous works have focused on understanding the recollection abilities of LLMs or their ability to identify imponderable/unanswerable questions, we believe there is a need for an effective AA evaluation method. Therefore, we propose a black-box evaluation methodology to examine and understand the AA of LLMs across a variety of multiple-choice QA tasks. We measure AA by rewarding models for abstaining from answering when their predictions are incorrect or when the questions are inherently unanswerable. We investigate three strategies, Strict Prompting, Verbal Confidence Thresholding, and Chain-of-Thought (CoT), to understand their impact on abstention across different LLMs. Our findings reveal that while even state-of-the-art LLMs like GPT-4 struggle with abstention, strategic prompting such as CoT, can significantly enhance this ability. Furthermore, we demonstrate that improving AA also leads to better overall QA task performance, underscoring the importance of evaluating AA in LLMs.

This paper presents an innovative exploration into the integration of interactive robotic musicianship within a commercial retail environment, specifically through a three-week-long in-store installation featuring a UR3 robotic arm, custom-built frame drums, and an adaptive music generation system. Situated in a prominent storefront in one of the world's largest cities, this project aimed to enhance the shopping experience by creating dynamic, engaging musical interactions that respond to the store's ambient soundscape. Key contributions include the novel application of industrial robotics in artistic expression, the deployment of interactive music to enrich retail ambiance, and the demonstration of continuous robotic operation in a public setting over an extended period. Challenges such as system reliability, variation in musical output, safety in interactive contexts, and brand alignment were addressed to ensure the installation's success. The project not only showcased the technical feasibility and artistic potential of robotic musicianship in retail spaces but also offered insights into the practical implications of such integration, including system reliability, the dynamics of human-robot interaction, and the impact on store operations. This exploration opens new avenues for enhancing consumer retail experiences through the intersection of technology, music, and interactive art, suggesting a future where robotic musicianship contributes meaningfully to public and commercial spaces.

Condé Nast, the media conglomerate that owns publications such as The New Yorker, Vogue and Wired, has sent a cease-and-desist letter to AI-powered search startup Perplexity, according to The Information. The letter, which was sent on Monday, demands that Perplexity stop using content from Condé Nast publications in its AI-generated responses and accused the startup of plagiarism. The move makes Condé Nast the latest in a growing list of publishers taking a stand against the unauthorized use of their content by AI companies, and comes a month after similar action taken by Forbes. Perplexity and Condé Nast did not immediately respond to a request for comment from Engadget. A recent investigation from Wired reveled that the startup's web crawlers do not respect robots.txt,

The first concert I bought tickets to after the pandemic subsided was a performance of the British singer-songwriter Birdy, held last April in Belgium. I've listened to Birdy more than to any other artist; her voice has pulled me through the hardest and happiest stretches of my life. I know every lyric to nearly every song in her discography, but that night Birdy's voice had the same effect as the first time I'd listened to her, through beat-up headphones connected to an iPod over a decade ago--a physical shudder, as if a hand had reached across time and grazed me, somehow, just beneath the skin. Countless people around the world have their own version of this ineffable connection, with Taylor Swift, perhaps, or the Beatles, Bob Marley, or Metallica. My feelings about Birdy's music were powerful enough to propel me across the Atlantic, just as tens of thousands of people flocked to the Sphere to see Phish earlier this year, or some 400,000 went to Woodstock in 1969.

Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM reasoning in recommendation systems (RecSys) presents a distinct challenge. RecSys tasks revolve around subjectivity and personalized preferences, an under-explored domain in utilizing LLMs' reasoning capabilities. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves by utilizing LLM reasoning in both zero-shot and finetuning settings. Additionally, we propose RecSAVER (Recommender Systems Automatic Verification and Evaluation of Reasoning) to automatically assess the quality of LLM reasoning responses without the requirement of curated gold references or human raters. We show that our framework aligns with real human judgment on the coherence and faithfulness of reasoning responses. Overall, our work shows that incorporating reasoning into RecSys can improve personalized tasks, paving the way for further advancements in recommender system methodologies.

The following contribution introduces a concept that employs Large Language Models (LLMs) and a chatbot interface to enhance SPARQL query generation for ontologies, thereby facilitating intuitive access to formalized knowledge. Utilizing natural language inputs, the system converts user inquiries into accurate SPARQL queries that strictly query the factual content of the ontology, effectively preventing misinformation or fabrication by the LLM. To enhance the quality and precision of outcomes, additional textual information from established domain-specific standards is integrated into the ontology for precise descriptions of its concepts and relationships. An experimental study assesses the accuracy of generated SPARQL queries, revealing significant benefits of using LLMs for querying ontologies and highlighting areas for future research.

Artificial intelligence (AI) systems have become an indispensable component of modern technology. However, research on human behavioral responses is lagging behind, i.e., the research into human reliance on AI advice (AI reliance). Current shortcomings in the literature include the unclear influences on AI reliance, lack of external validity, conflicting approaches to measuring reliance, and disregard for a change in reliance over time. Promising avenues for future research include reliance on generative AI output and reliance in multi-user situations. In conclusion, we present a morphological box that serves as a guide for research on AI reliance.

Social Media platforms have offered invaluable opportunities for linguistic research. The availability of up-to-date data, coming from any part in the world, and coming from natural contexts, has allowed researchers to study language in real time. One of the fields that has made great use of social media platforms is Corpus Linguistics. There is currently a wide range of projects which have been able to successfully create corpora from social media. In this paper, we present the development and deployment of a linguistic corpus from Twitter posts in English, coming from 26 news agencies and 27 individuals. The main goal was to create a fully annotated English corpus for linguistic analysis. We include information on morphology and syntax, as well as NLP features such as tokenization, lemmas, and n- grams. The information is presented through a range of powerful visualisations for users to explore linguistic patterns in the corpus. With this tool, we aim to contribute to the area of language technologies applied to linguistic research.

Large multimodal models (LMMs) are processing increasingly longer and richer inputs. Albeit the progress, few public benchmark is available to measure such development. To mitigate this gap, we introduce LongVideoBench, a question-answering benchmark that features video-language interleaved inputs up to an hour long. Our benchmark includes 3,763 varying-length web-collected videos with their subtitles across diverse themes, designed to comprehensively evaluate LMMs on long-term multimodal understanding. To achieve this, we interpret the primary challenge as to accurately retrieve and reason over detailed multimodal information from long inputs. As such, we formulate a novel video question-answering task termed referring reasoning. Specifically, as part of the question, it contains a referring query that references related video contexts, called referred context. The model is then required to reason over relevant video details from the referred context. Following the paradigm of referring reasoning, we curate 6,678 human-annotated multiple-choice questions in 17 fine-grained categories, establishing one of the most comprehensive benchmarks for long-form video understanding. Evaluations suggest that the LongVideoBench presents significant challenges even for the most advanced proprietary models (e.g. GPT-4o, Gemini-1.5-Pro, GPT-4-Turbo), while their open-source counterparts show an even larger performance gap. In addition, our results indicate that model performance on the benchmark improves only when they are capable of processing more frames, positioning LongVideoBench as a valuable benchmark for evaluating future-generation long-context LMMs.

Language agents, built on top of language models (LMs), are systems that can interact with complex environments, such as the open web. In this work, we examine whether such agents can perform realistic and time-consuming tasks on the web, e.g., monitoring real-estate markets or locating relevant nearby businesses. We introduce AssistantBench, a challenging new benchmark consisting of 214 realistic tasks that can be automatically evaluated, covering different scenarios and domains. We find that AssistantBench exposes the limitations of current systems, including language models and retrieval-augmented language models, as no model reaches an accuracy of more than 25 points. While closed-book LMs perform well, they exhibit low precision since they tend to hallucinate facts. State-of-the-art web agents reach a score of near zero. Additionally, we introduce SeePlanAct (SPA), a new web agent that significantly outperforms previous agents, and an ensemble of SPA and closed-book models reaches the best overall performance. Moreover, we analyze failures of current systems and highlight that web navigation remains a major challenge.