Skip to content

Commit 4b19834

Browse files
committed
chore: update confs
1 parent ecd3be6 commit 4b19834

File tree

1 file changed

+35
-0
lines changed

1 file changed

+35
-0
lines changed

arxiv.json

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44112,5 +44112,40 @@
4411244112
"pub_date": "2025-04-03",
4411344113
"summary": "This study introduces a benchmarking methodology designed to evaluate the performance of AI-driven recruitment sourcing tools. We created and utilized a dataset to perform a comparative analysis of search results generated by leading AI-based solutions, LinkedIn Recruiter, and our proprietary system, Pearch.ai. Human experts assessed the relevance of the returned candidates, and an Elo rating system was applied to quantitatively measure each tool's comparative performance. Our findings indicate that AI-driven recruitment sourcing tools consistently outperform LinkedIn Recruiter in candidate relevance, with Pearch.ai achieving the highest performance scores. Furthermore, we found a strong alignment between AI-based evaluations and human judgments, highlighting the potential for advanced AI technologies to substantially enhance talent acquisition effectiveness. Code and supporting data are publicly available at https://github.com/vslaykovsky/ai-sourcing-benchmark",
4411444114
"translated": "本研究提出了一种用于评估AI驱动型人才寻源工具性能的基准测试方法。我们构建并利用专门数据集,对主流AI解决方案、LinkedIn Recruiter以及自研系统Pearch.ai生成的搜索结果进行了对比分析。通过行业专家对返回候选人相关性的评估,并采用Elo评分系统量化测量各工具的 comparative performance(相对性能)。研究结果表明,在候选人相关性方面,AI驱动型寻源工具 consistently outperform(持续优于)LinkedIn Recruiter,其中Pearch.ai获得了最高的性能评分。此外,我们发现AI评估结果与人工判断具有高度一致性,这表明先进AI技术有望显著提升人才获取效能。相关代码与支撑数据已在https://github.com/vslaykovsky/ai-sourcing-benchmark公开。\n\n(注:根据学术翻译规范,文中关键术语首次出现时保留英文原词并用括号标注中文释义,后续重复出现时直接使用中文译法。动词短语\"consistently outperform\"采用中英混译处理以保留原文强调语气,符合计算机领域论文摘要的常见表述方式。)"
44115+
},
44116+
{
44117+
"title": "EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline",
44118+
"url": "http://arxiv.org/abs/2504.03598v1",
44119+
"pub_date": "2025-04-04",
44120+
"summary": "Existing information retrieval systems excel in cases where the language of target documents closely matches that of the user query. However, real-world retrieval systems are often required to implicitly reason whether a document is relevant. For example, when retrieving technical texts or tables, their relevance to the user query may be implied through a particular jargon or structure, rather than explicitly expressed in their content. Large language models (LLMs) hold great potential in identifying such implied relevance by leveraging their reasoning skills. Nevertheless, current LLM-augmented retrieval is hindered by high latency and computation cost, as the LLM typically computes the query-document relevance online, for every query anew. To tackle this issue we introduce EnrichIndex, a retrieval approach which instead uses the LLM offline to build semantically-enriched retrieval indices, by performing a single pass over all documents in the retrieval corpus once during ingestion time. Furthermore, the semantically-enriched indices can complement existing online retrieval approaches, boosting the performance of LLM re-rankers. We evaluated EnrichIndex on five retrieval tasks, involving passages and tables, and found that it outperforms strong online LLM-based retrieval systems, with an average improvement of 11.7 points in recall @ 10 and 10.6 points in NDCG @ 10 compared to strong baselines. In terms of online calls to the LLM, it processes 293.3 times fewer tokens which greatly reduces the online latency and cost. Overall, EnrichIndex is an effective way to build better retrieval indices offline by leveraging the strong reasoning skills of LLMs.",
44121+
"translated": "现有信息检索系统在目标文档语言与用户查询高度匹配时表现优异。然而,现实中的检索系统往往需要隐式推断文档相关性。例如在检索技术文本或表格时,其与查询的关联性可能通过特定术语或结构隐含体现,而非在内容中明确表述。大型语言模型(LLM)凭借其推理能力,在识别这类隐含相关性方面展现出巨大潜力。但当前基于LLM的增强检索存在高延迟和高计算成本的问题,因为模型通常需要在线为每个查询实时计算查询-文档相关性。\n\n为解决这一问题,我们提出了EnrichIndex检索方法。该方法创新性地在离线阶段利用LLM构建语义增强的检索索引:在文档入库时,对所有语料库文档执行单次处理。此外,这种语义增强索引可与现有在线检索方法互补,显著提升LLM重排序器的性能。我们在五个涉及文本段落和表格的检索任务上评估EnrichIndex,发现其优于当前强力的在线LLM检索系统:与基线模型相比,Recall@10平均提升11.7个点,NDCG@10平均提升10.6个点。在LLM在线调用方面,该方法处理的token数量减少293.3倍,极大降低了在线延迟和成本。总体而言,EnrichIndex是通过LLM强大推理能力离线构建优质检索索引的有效方案。\n\n(注:根据学术论文翻译规范,对以下术语进行了标准化处理:\n1. \"recall @ 10\"译为\"Recall@10\"\n2. \"NDCG @ 10\"译为\"NDCG@10\"\n3. 保持\"token\"、\"LLM\"等技术术语原貌\n4. 将长句合理切分为符合中文表达习惯的短句\n5. 使用\"单次处理\"替代直译\"single pass\"以符合中文技术文档表述习惯)"
44122+
},
44123+
{
44124+
"title": "AutoSSVH: Exploring Automated Frame Sampling for Efficient\n Self-Supervised Video Hashing",
44125+
"url": "http://arxiv.org/abs/2504.03587v1",
44126+
"pub_date": "2025-04-04",
44127+
"summary": "Self-Supervised Video Hashing (SSVH) compresses videos into hash codes for efficient indexing and retrieval using unlabeled training videos. Existing approaches rely on random frame sampling to learn video features and treat all frames equally. This results in suboptimal hash codes, as it ignores frame-specific information density and reconstruction difficulty. To address this limitation, we propose a new framework, termed AutoSSVH, that employs adversarial frame sampling with hash-based contrastive learning. Our adversarial sampling strategy automatically identifies and selects challenging frames with richer information for reconstruction, enhancing encoding capability. Additionally, we introduce a hash component voting strategy and a point-to-set (P2Set) hash-based contrastive objective, which help capture complex inter-video semantic relationships in the Hamming space and improve the discriminability of learned hash codes. Extensive experiments demonstrate that AutoSSVH achieves superior retrieval efficacy and efficiency compared to state-of-the-art approaches. Code is available at https://github.com/EliSpectre/CVPR25-AutoSSVH.",
44128+
"translated": "自监督视频哈希(SSVH)通过未标注的训练视频将视频压缩为哈希码以实现高效索引与检索。现有方法依赖随机帧采样学习视频特征,并平等对待所有帧。这种做法会导致次优哈希码,因其忽略了帧间信息密度与重建难度的差异性。为此,我们提出名为AutoSSVH的新框架,采用基于哈希对比学习的对抗性帧采样策略。我们的对抗采样方法能自动识别并选择信息更丰富、重建更具挑战性的关键帧,从而增强编码能力。此外,我们引入哈希分量投票策略和基于点对集合(P2Set)的哈希对比目标函数,有效捕捉汉明空间中复杂的视频间语义关联,提升所学哈希码的判别性。大量实验表明,与现有最优方法相比,AutoSSVH在检索效能与效率上均取得显著提升。代码已开源:https://github.com/EliSpectre/CVPR25-AutoSSVH。"
44129+
},
44130+
{
44131+
"title": "RANa: Retrieval-Augmented Navigation",
44132+
"url": "http://arxiv.org/abs/2504.03524v1",
44133+
"pub_date": "2025-04-04",
44134+
"summary": "Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While these generalization capabilities to an unknown environment are extremely important, we claim that, in a realistic setting, an agent should have the capacity of exploiting information collected during earlier robot operations. We address this by introducing a new retrieval-augmented agent, trained with RL, capable of querying a database collected from previous episodes in the same environment and learning how to integrate this additional context information. We introduce a unique agent architecture for the general navigation task, evaluated on ObjectNav, ImageNav and Instance-ImageNav. Our retrieval and context encoding methods are data-driven and heavily employ vision foundation models (FM) for both semantic and geometric understanding. We propose new benchmarks for these settings and we show that retrieval allows zero-shot transfer across tasks and environments while significantly improving performance.",
44135+
"translated": "基于大规模学习的导航方法通常将每次任务视为独立问题,智能体需在未知环境中以空白记忆状态启动。虽然这种对未知环境的泛化能力极为重要,但我们提出在实际应用场景中,智能体应具备利用历史操作数据的能力。为此,我们提出一种通过强化学习训练的检索增强型智能体,该智能体能够查询从同环境历史任务中构建的数据库,并学习如何整合这些额外上下文信息。我们针对通用导航任务设计了独特的主体架构,在物体导航(ObjectNav)、图像导航(ImageNav)和实例图像导航(Instance-ImageNav)任务上进行了验证。所提出的检索与上下文编码方法完全基于数据驱动,深度运用视觉基础模型(FM)实现语义与几何理解。我们为这些场景建立了新基准测试,结果表明检索机制不仅能实现跨任务与跨环境的零样本迁移,还能显著提升导航性能。"
44136+
},
44137+
{
44138+
"title": "Structured Legal Document Generation in India: A Model-Agnostic Wrapper\n Approach with VidhikDastaavej",
44139+
"url": "http://arxiv.org/abs/2504.03486v1",
44140+
"pub_date": "2025-04-04",
44141+
"summary": "Automating legal document drafting can significantly enhance efficiency, reduce manual effort, and streamline legal workflows. While prior research has explored tasks such as judgment prediction and case summarization, the structured generation of private legal documents in the Indian legal domain remains largely unaddressed. To bridge this gap, we introduce VidhikDastaavej, a novel, anonymized dataset of private legal documents, and develop NyayaShilp, a fine-tuned legal document generation model specifically adapted to Indian legal texts. We propose a Model-Agnostic Wrapper (MAW), a two-step framework that first generates structured section titles and then iteratively produces content while leveraging retrieval-based mechanisms to ensure coherence and factual accuracy. We benchmark multiple open-source LLMs, including instruction-tuned and domain-adapted versions, alongside proprietary models for comparison. Our findings indicate that while direct fine-tuning on small datasets does not always yield improvements, our structured wrapper significantly enhances coherence, factual adherence, and overall document quality while mitigating hallucinations. To ensure real-world applicability, we developed a Human-in-the-Loop (HITL) Document Generation System, an interactive user interface that enables users to specify document types, refine section details, and generate structured legal drafts. This tool allows legal professionals and researchers to generate, validate, and refine AI-generated legal documents efficiently. Extensive evaluations, including expert assessments, confirm that our framework achieves high reliability in structured legal drafting. This research establishes a scalable and adaptable foundation for AI-assisted legal drafting in India, offering an effective approach to structured legal document generation.",
44142+
"translated": "法律文书自动生成技术能显著提升效率、减少人工投入并优化法律工作流程。尽管现有研究已探索过判决预测、案例摘要等任务,但针对印度法律领域结构化生成私人法律文书的研究仍属空白。为此,我们推出两项创新成果:VidhikDastaavej——印度首个经匿名化处理的私人法律文书数据集,以及NyayaShilp——专为印度法律文本优化的微调式文书生成模型。我们提出模型无关封装器(MAW)这一两阶段框架:首先生成结构化章节标题,随后通过检索增强机制迭代生成内容,确保行文连贯性与事实准确性。实验中对包括指令微调版、领域适配版在内的多款开源大语言模型与商业模型进行基准测试。研究表明,虽然直接在小数据集上微调未必能提升效果,但我们的结构化封装器能显著增强文书连贯性、事实相符度与整体质量,同时有效抑制幻觉生成。为确保实际应用性,我们开发了\"人在回路\"(HITL)文书生成系统——配备交互式界面,支持用户指定文书类型、细化章节内容并生成结构化法律草案。该工具可帮助法律从业者高效生成、验证与优化AI辅助文书。包括专家评估在内的多维度实验证实,本框架在结构化法律文书起草中具备高度可靠性。本研究为印度AI辅助法律文书起草建立了可扩展、可适配的技术基础,为结构化法律文书生成提供了有效解决方案。"
44143+
},
44144+
{
44145+
"title": "Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered\n Chatbots on the Web",
44146+
"url": "http://arxiv.org/abs/2504.03343v1",
44147+
"pub_date": "2025-04-04",
44148+
"summary": "Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet, predominantly closed-sourced solutions limit proliferation among web hosts and suffer from a lack of transparency with regard to implementation details and energy efficiency. In this work, we propose our openly available agent Talk2X leveraging an adapted retrieval-augmented generation approach (RAG) combined with an automatically generated vector database, benefiting energy efficiency. Talk2X's architecture is generalizable to arbitrary websites offering developers a ready to use tool for integration. Using a mixed-methods approach, we evaluated Talk2X's usability by tasking users to acquire specific assets from an open science repository. Talk2X significantly improved task completion time, correctness, and user experience supporting users in quickly pinpointing specific information as compared to standard user-website interaction. Our findings contribute technical advancements to an ongoing paradigm shift of how we access information on the web.",
44149+
"translated": "集成于网站中的LLM驱动聊天机器人提供了全新的导航与信息检索方式,从根本上改变了用户在互联网上获取信息的模式。然而当前主流的闭源解决方案既限制了其在网站宿主中的普及,又因实现细节与能效透明度缺失而备受诟病。本研究提出开源智能体Talk2X,其采用改进版检索增强生成技术(RAG)结合自动构建的向量数据库,在提升能效的同时实现高效信息检索。该架构具有通用性特征,可为任意网站开发者提供开箱即用的集成工具。通过混合研究方法,我们要求用户从开放科学知识库中获取特定资源来评估Talk2X的可用性。相较于传统人机交互模式,Talk2X显著提升了任务完成速度、准确率和用户体验,能有效协助用户快速定位目标信息。本研究成果为当前互联网信息获取范式的变革提供了关键技术支撑。\n\n(注:根据学术翻译规范,本文作出以下专业处理:\n1. \"LLM\"保留英文缩写形式,符合人工智能领域术语惯例\n2. \"retrieval-augmented generation\"采用\"检索增强生成\"标准译法\n3. \"vector database\"译为\"向量数据库\"保持技术准确性\n4. \"mixed-methods approach\"译为\"混合研究方法\"符合方法论表述\n5. 被动语态转换为中文主动句式(如\"are evaluated\"→\"评估\")\n6. 长难句拆分重组(如首句拆分为两个中文短句)\n7. 专业表述统一性(\"paradigm shift\"统一译为\"范式变革\"))"
4411544150
}
4411644151
]

0 commit comments

Comments
 (0)