English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination (NAACL 2024)

Forum topic · 小凯 · 2026-07-05

Summary

This NAACL 2024 paper, indexed on zhichai.net, addresses personalization of LLM-based medical assistants through coordination between short-term and long-term memory. The work falls at the intersection of information retrieval and large language model systems, focusing on how conversational context (short-term memory) can be combined with persistent user history and knowledge (long-term memory) to deliver personalized medical assistance. The forum entry situates the paper within the broader personalization landscape spanning retrieval-augmented generation (RAG), agentic search, and user-context modeling. It outlines a general system pipeline covering input representation, core modules (retriever, reranker, planner, memory units), learning strategies such as supervised fine-tuning and reinforcement learning, and inference strategies including iterative retrieval with budget control. The entry also discusses evaluation practices (nDCG, MRR, Recall@k, human preference), engineering deployment constraints such as latency budgets, PII handling, safety, and cost, and open problems including evaluation trustworthiness, hallucination, and cross-lingual generalization. Related entries include surveys on personalization from RAG to agents, User-LLM user embeddings, and personalized retrieval systems. Readers should consult the original PDF at aclanthology.org for exact quantitative results, as this digest is based on metadata and abstract-level information.

LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination (NAACL 2024)

Overview

This forum entry indexes a NAACL 2024 paper on LLM-based medical assistant personalization with coordination between short-term and long-term memory.

  • Venue: NAACL 2024
  • Link: https://aclanthology.org/2024.naacl-long.132/
  • Category: Personalization
  • Research Context

    The paper addresses a core question for LLM-era search and personalization systems: how to reallocate responsibilities among retrieval, ranking, generation, and tool invocation. Personalized medical assistance requires both:

  • Short-term memory — the current conversational context and immediate user intent;
  • Long-term memory — persistent user history, preferences, and domain knowledge.
  • Traditional pipelines that treat retrieval, ranking, and generation as separate stages struggle to meet user expectations for natural-language interaction and multi-hop reasoning, motivating a memory-coordinated personalization approach.

    Method Structure

    Following the typical four-stage pattern of such systems:

    1. Input & representation — encoding queries, documents, and user context into dense/sparse representations or structured prompts; 2. Core modules — retriever, reranker, planner, memory modules, and tool interfaces, arranged serially or in parallel; 3. Learning strategy — supervised fine-tuning, contrastive learning, distillation, or reinforcement learning; 4. Inference strategy — single-turn vs. iterative retrieval, early stopping, and compute budget control.

    Evaluation & Engineering Considerations

    Typical evaluation covers nDCG@10, MRR, Recall@k, human preference, and task success rates. For deployment in medical settings, key engineering checklist items include:

    | Concern | Recommendation | |---------|----------------| | Data | PII partitioning, sanitization, versioned embeddings | | Latency | Cascaded retrieval with early stopping, caching | | Safety | Source whitelisting, hallucination filtering | | Cost | Model routing, distillation, hybrid sparse+dense retrieval |

    Insights for Personalization

    1. Architecture: cascaded retrieval + reranking + generation remains mainstream, but agentic paradigms make retrieval policy itself learnable; 2. Data: high-quality instruction data and session logs are as critical as model architecture; 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs human cross-validation; 4. Product: latency, cost, explainability, and safety are hard constraints in medical deployment.

    Related Entries

  • A Survey of Personalization: From RAG to Agent (arXiv 2504.10147)
  • Bridging Personalization and Control in Scientific Personalized Search (arXiv 2411.02790)
  • IntentRec: Predicting User Session Intent (arXiv 2408.05353)
  • Unified Embedding-Based Personalized Retrieval in Etsy Search (arXiv 2306.04833)
  • User-LLM: Efficient LLM Contextualization with User Embeddings (WWW)
> Note: Quantitative results should be verified against the original PDF. This digest is compiled from abstract-level and public metadata.

Glossary

| Term | Meaning | |------|---------| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | nDCG | Normalized Discounted Cumulative Gain | | Agentic Search | Modeling search as sequential decision-making and tool invocation | | Gen-IR | Generative Information Retrieval |

Tags

#llm#personalization#medical-ai#memory#retrieval-augmented-generation#naacl-2024#conversational-ai

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208794