SGMem: Sentence Graph Memory for Long-Term Conversational Agents
Long-term conversational agents require effective memory management to handle dialogue histories that exceed the context window of large language models (LLMs). Existing methods based on fact extraction or summarization reduce redundancy but struggle to organize and retrieve relevant information across different granularities of dialogue and generated memory. We introduce SGMem (Sentence Graph Memory), which represents dialogue as sentence-level graphs within chunked units, capturing associations across turn-, round-, and session-level contexts. By combining retrieved raw dialogue with generated memory such as summaries, facts and insights, SGMem supplies LLMs with coherent and relevant context for response generation. Experiments on LongMemEval and LoCoMo show that SGMem consistently improves accuracy and outperforms strong baselines in long-term conversational question answering.
Code (0)
등록된 구현이 없습니다.
Tasks
Conversational Question AnsweringResponse GenerationSimilar Papers 제목 키워드 기반
Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval
This paper develops a model that addresses sentence embedding, a hot topic in current natural language processing research, using recurrent neural networks with Long Short-Term Memory (LSTM) cells. Due to its ability to …
Information RetrievalRetrievalSentenceSentence Embedding+1A Hierarchical Neural Autoencoder for Paragraphs and Documents
Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: trai…
SentenceText GenerationCombining Long Short Term Memory and Convolutional Neural Network for Cross-Sentence n-ary Relation Extraction
We propose in this paper a combined model of Long Short Term Memory and Convolutional Neural Networks (LSTM-CNN) that exploits word embeddings and positional embeddings for cross-sentence n-ary relation extraction. The p…
RelationRelation ExtractionSentenceWord EmbeddingsRead, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based Approach
Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way…
Abstractive Text SummarizationGPUHard AttentionLEMMA+5