chore: update confs

arxiv.json

@@ -38470,5 +38470,40 @@
         "pub_date": "2025-01-09",
         "summary": "In this work, we explore the application of Large Language Models to zero-shot Lay Summarisation. We propose a novel two-stage framework for Lay Summarisation based on real-life processes, and find that summaries generated with this method are increasingly preferred by human judges for larger models. To help establish best practices for employing LLMs in zero-shot settings, we also assess the ability of LLMs as judges, finding that they are able to replicate the preferences of human judges. Finally, we take the initial steps towards Lay Summarisation for Natural Language Processing (NLP) articles, finding that LLMs are able to generalise to this new domain, and further highlighting the greater utility of summaries generated by our proposed approach via an in-depth human evaluation.",
         "translated": "在这项工作中，我们探索了大型语言模型在零样本浅层摘要生成中的应用。我们提出了一种基于现实生活过程的新型两阶段框架用于浅层摘要生成，并发现随着模型规模的增大，人类评审员越来越倾向于使用该方法生成的摘要。为了帮助确立在零样本设置中使用大型语言模型的最佳实践，我们还评估了大型语言模型作为评审员的能力，发现它们能够复制人类评审员的偏好。最后，我们迈出了自然语言处理（NLP）文章浅层摘要生成的第一步，发现大型语言模型能够泛化到这一新领域，并通过深入的人类评估进一步凸显了我们提出的方法生成的摘要具有更大的实用性。"
+    },
+    {
+        "title": "kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search",
+        "url": "http://arxiv.org/abs/2501.06121v1",
+        "pub_date": "2025-01-10",
+        "summary": "Approximate Nearest Neighbors (ANN) search is a crucial task in several applications like recommender systems and information retrieval. Current state-of-the-art ANN libraries, although being performance-oriented, often lack modularity and ease of use. This translates into them not being fully suitable for easy prototyping and testing of research ideas, an important feature to enable. We address these limitations by introducing kANNolo, a novel research-oriented ANN library written in Rust and explicitly designed to combine usability with performance effectively. kANNolo is the first ANN library that supports dense and sparse vector representations made available on top of different similarity measures, e.g., euclidean distance and inner product. Moreover, it also supports vector quantization techniques, e.g., Product Quantization, on top of the indexing strategies implemented. These functionalities are managed through Rust traits, allowing shared behaviors to be handled abstractly. This abstraction ensures flexibility and facilitates an easy integration of new components. In this work, we detail the architecture of kANNolo and demonstrate that its flexibility does not compromise performance. The experimental analysis shows that kANNolo achieves state-of-the-art performance in terms of speed-accuracy trade-off while allowing fast and easy prototyping, thus making kANNolo a valuable tool for advancing ANN research. Source code available on GitHub: https://github.com/TusKANNy/kannolo.",
+        "translated": "近似最近邻（Approximate Nearest Neighbors, ANN）搜索在推荐系统和信息检索等应用中是一项关键任务。当前最先进的ANN库虽然以性能为导向，但通常缺乏模块化和易用性。这导致它们不太适合快速原型设计和研究想法的测试，而这些功能是非常重要的。我们通过引入kANNolo来解决这些限制，这是一个用Rust编写的新型研究导向型ANN库，旨在有效结合可用性和性能。kANNolo是第一个支持稠密和稀疏向量表示的ANN库，这些表示可以在不同的相似性度量（如欧几里得距离和内积）上使用。此外，它还支持在已实现的索引策略之上使用向量量化技术，例如乘积量化（Product Quantization）。这些功能通过Rust的特性（traits）进行管理，使得共享行为可以被抽象地处理。这种抽象确保了灵活性，并便于新组件的集成。在本研究中，我们详细介绍了kANNolo的架构，并证明其灵活性不会影响性能。实验分析表明，kANNolo在速度-精度权衡方面达到了最先进的性能，同时允许快速且简便的原型设计，从而使kANNolo成为推动ANN研究的宝贵工具。源代码可在GitHub上获取：https://github.com/TusKANNy/kannolo。"
+    },
+    {
+        "title": "Recommender Systems for Social Good: The Role of Accountability and\n  Sustainability",
+        "url": "http://arxiv.org/abs/2501.05964v1",
+        "pub_date": "2025-01-10",
+        "summary": "This work examines the role of recommender systems in promoting sustainability, social responsibility, and accountability, with a focus on alignment with the United Nations Sustainable Development Goals (SDGs). As recommender systems become increasingly integrated into daily interactions, they must go beyond personalization to support responsible consumption, reduce environmental impact, and foster social good. We explore strategies to mitigate the carbon footprint of recommendation models, ensure fairness, and implement accountability mechanisms. By adopting these approaches, recommender systems can contribute to sustainable and socially beneficial outcomes, aligning technological advancements with the SDGs focused on environmental sustainability and social well-being.",
+        "translated": "本研究探讨了推荐系统在促进可持续性、社会责任和问责制方面的作用，重点关注与联合国可持续发展目标（SDGs）的一致性。随着推荐系统日益融入日常交互中，它们必须超越个性化，支持负责任的消费、减少环境影响并促进社会公益。我们探索了降低推荐模型碳足迹、确保公平性以及实施问责机制的策略。通过采用这些方法，推荐系统可以为可持续和社会有益的结果做出贡献，将技术进步与专注于环境可持续性和社会福祉的可持续发展目标相一致。"
+    },
+    {
+        "title": "Navigating Tomorrow: Reliably Assessing Large Language Models\n  Performance on Future Event Prediction",
+        "url": "http://arxiv.org/abs/2501.05925v1",
+        "pub_date": "2025-01-10",
+        "summary": "Predicting future events is an important activity with applications across multiple fields and domains. For example, the capacity to foresee stock market trends, natural disasters, business developments, or political events can facilitate early preventive measures and uncover new opportunities. Multiple diverse computational methods for attempting future predictions, including predictive analysis, time series forecasting, and simulations have been proposed. This study evaluates the performance of several large language models (LLMs) in supporting future prediction tasks, an under-explored domain. We assess the models across three scenarios: Affirmative vs. Likelihood questioning, Reasoning, and Counterfactual analysis. For this, we create a dataset1 by finding and categorizing news articles based on entity type and its popularity. We gather news articles before and after the LLMs training cutoff date in order to thoroughly test and compare model performance. Our research highlights LLMs potential and limitations in predictive modeling, providing a foundation for future improvements.",
+        "translated": "预测未来事件是一项重要的活动，在多个领域和行业中具有广泛的应用。例如，预见股市趋势、自然灾害、商业发展或政治事件的能力能够促进早期预防措施的实施，并发现新的机遇。目前，已经提出了多种多样用于未来预测的计算方法，包括预测分析、时间序列预测和模拟等。本研究评估了几种大型语言模型（LLMs）在支持未来预测任务中的表现，这是一个尚未充分探索的领域。我们从三个场景对模型进行了评估：肯定性提问与可能性提问、推理以及反事实分析。为此，我们通过根据实体类型及其流行度查找和分类新闻文章，创建了一个数据集1。我们收集了LLMs训练截止日期之前和之后的新闻文章，以全面测试和比较模型的表现。我们的研究突出了LLMs在预测建模中的潜力和局限性，为未来的改进提供了基础。"
+    },
+    {
+        "title": "Text2Playlist: Generating Personalized Playlists from Text on Deezer",
+        "url": "http://arxiv.org/abs/2501.05894v1",
+        "pub_date": "2025-01-10",
+        "summary": "The streaming service Deezer heavily relies on the search to help users navigate through its extensive music catalog. Nonetheless, it is primarily designed to find specific items and does not lead directly to a smooth listening experience. We present Text2Playlist, a stand-alone tool that addresses these limitations. Text2Playlist leverages generative AI, music information retrieval and recommendation systems to generate query-specific and personalized playlists, successfully deployed at scale.",
+        "translated": "流媒体服务Deezer在很大程度上依赖搜索功能来帮助用户浏览其庞大的音乐目录。然而，该搜索功能主要是为了查找特定项目而设计的，并不能直接带来流畅的听歌体验。我们提出了Text2Playlist，一个独立的工具，旨在解决这些局限性。Text2Playlist结合了生成式人工智能、音乐信息检索和推荐系统，能够生成与查询相关且个性化的播放列表，并已成功大规模部署。"
+    },
+    {
+        "title": "VideoRAG: Retrieval-Augmented Generation over Video Corpus",
+        "url": "http://arxiv.org/abs/2501.05874v1",
+        "pub_date": "2025-01-10",
+        "summary": "Retrieval-Augmented Generation (RAG) is a powerful strategy to address the issue of generating factually incorrect outputs in foundation models by retrieving external knowledge relevant to queries and incorporating it into their generation process. However, existing RAG approaches have primarily focused on textual information, with some recent advancements beginning to consider images, and they largely overlook videos, a rich source of multimodal knowledge capable of representing events, processes, and contextual details more effectively than any other modality. While a few recent studies explore the integration of videos in the response generation process, they either predefine query-associated videos without retrieving them according to queries, or convert videos into the textual descriptions without harnessing their multimodal richness. To tackle these, we introduce VideoRAG, a novel framework that not only dynamically retrieves relevant videos based on their relevance with queries but also utilizes both visual and textual information of videos in the output generation. Further, to operationalize this, our method revolves around the recent advance of Large Video Language Models (LVLMs), which enable the direct processing of video content to represent it for retrieval and seamless integration of the retrieved videos jointly with queries. We experimentally validate the effectiveness of VideoRAG, showcasing that it is superior to relevant baselines.",
+        "translated": "检索增强生成（Retrieval-Augmented Generation, RAG）是一种强大的策略，旨在通过检索与查询相关的外部知识并将其整合到生成过程中，来解决基础模型生成事实错误输出的问题。然而，现有的RAG方法主要集中在文本信息上，尽管最近的一些进展开始考虑图像，但它们大多忽视了视频这一多模态知识的丰富来源。视频能够比任何其他模态更有效地表示事件、过程和上下文细节。尽管最近有几项研究探索了在响应生成过程中整合视频的方法，但它们要么预定义了与查询相关的视频而不根据查询进行检索，要么将视频转换为文本描述，而没有充分利用其多模态的丰富性。\n\n为了解决这些问题，我们提出了VideoRAG，这是一个新颖的框架，不仅能够根据视频与查询的相关性动态检索相关视频，还能在输出生成过程中利用视频的视觉和文本信息。此外，为了实现这一目标，我们的方法围绕最近的大规模视频语言模型（Large Video Language Models, LVLMs）的进展展开，这些模型能够直接处理视频内容以进行检索，并将检索到的视频与查询无缝整合。我们通过实验验证了VideoRAG的有效性，展示了其优于相关基线方法的性能。"
     }
 ]