Query-Variant Advertisement Text Generation with Association Knowledge

牢记于心：评估智能体记忆中的隐式关联盲点

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

研究智能体记忆中的隐式关联盲点问题，引入InMind基准测试，通过配对控制区分三种解释，实验发现将记忆置于上下文时主干回答间接查询比例高，检索相同记忆时其他系统召回率低，诊断探针可缩小差距，指出路由是关键问题。

缓解过度关联对对话式查询生成的负面影响

Mitigating the Negative Impact of Over-association for Conversational Query Production

本文针对对话式查询生成中因金标查询与对话主题过度关联导致的数据饥饿和概念偏差问题，提出实例级加权训练策略，在Wizard-of-Internet和DuSinc上实现2%-5%的性能提升，并将数据效率提高10倍。

作为抽象语义关联评估的情节检索

Plot Retrieval as an Assessment of Abstract Semantic Association

本文构建低词重叠、重抽象语义关联的标注数据集 Plot Retrieval，并通过多类检索方法与人类对比，评估 IR 模型捕捉抽象语义关联的能力。

从关联到因果：通过因果关系与注意力机制提升检索增强生成的检索精度

From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism

该研究针对RAG检索阶段仅捕捉关联关系的问题，通过建模检索过程的因果结构，提出一种无需训练的注意力式重评分规则，在企业知识库和关键词堆砌语料库上显著提升了检索精度。

关联并非相似性：为多跳检索学习语料特定的关联

Association Is Not Similarity: Learning Corpus-Specific Associations for Multi-Hop Retrieval

本文提出AAR方法，通过对比学习在嵌入空间中学习语料特定的关联关系，提升多跳检索的召回率，且无需评估集调优。

当错误的键胜出：理解并检测大语言模型中的幻觉

When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

本文通过潜在键视角揭示大语言模型幻觉源于预训练关联竞争，提出两阶段关键词扰动检测法，在多个基准上达0.910 AUROC，并统一解释四种幻觉机制。

Madeleine：从模拟生活中学习对话记忆的非自愿回忆

Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives

Madeleine通过离线模拟生活学习记忆关联，在线零LLM调用，仅替换查询编码器，在LoCoMo-Plus上达到最高分并大幅提升基线。

癌症实体关联与分类的机器学习方法

Machine Learning Approach for Cancer Entities Association and Classification

本研究利用NLP技术中的命名实体识别和文本分类，结合机器学习分类器与SQL，从海量生物医学文献中提取癌症相关实体并发现隐藏关联，以推进癌症研究。

Generation-Augmented Query Expansion For Code Retrieval

Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus only on optimizing the documentation code pairs by embedding them into latent space, without the association of external knowledge. In this paper, we propose a generation-augmented query expansion framework. Inspired by the human retrieval process - sketching an answer before searching, in this work, we utilize the powerful code generation model to benefit the code retrieval tas…

Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering

Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is considered as a challenging problem since i) no supervision is given to the reasoning process and ii) high-order semantics of multi-hop knowledge facts need to be captured. In this paper, we introduce a concept of hypergraph to encode high-level semantics of a question and a knowledge base, and to learn high-order associations between them. The proposed mod…

Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization

Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based knowledge source such as an ontology like the UMLS. Moreover, hidden associations between candidate concepts meaningful in the current context, may not exist within a single document, but within the collection, via alternate lexical forms. Therefore, inspired by the recent success of sequence-to-sequence neural models in delivering the state-of-the-art in a…