본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
로그인 회원가입 English 국회부산도서관

전체메뉴

HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색

결과 내 검색

동의어 포함

고급검색

인명/단체명

저자정보 상세정보
인명/단체명을 입력하세요.

키워드

  • 대표어

  • 외국어

-

초록보기

Large language models (LLMs) maintain coherence over a few thousand tokens but degrade sharply in multi hundred turn conversations. We present a hippocampus inspired dual memory architecture that separates dialogue context into (1) Compact Memory, a continuously updated one sentence summary that preserves the global narrative, and (2) Vector Memory, an episodic store of chunk embeddings queried via cosine similarity. Integrated with an off the shelf 6B parameter transformer, the system sustains > 300 turn dialogues while keeping the prompt under 3.5 K tokens. On long form QA and story continuation benchmarks, Compact + Vector Memory elevates factual recall accuracy from 41 % to 87 % and human rated coherence from 2.7 to 4.3. Precision–recall analysis shows that, with 10 K indexed chunks, Vector Memory achieves P@5 ≥ 0.80 and R@50 ≥ 0.74, doubling the area under the PR curve relative to a summarisation only baseline. Ablation experiments reveal that (i) semantic forgetting—age weighted pruning of low salience chunks—cuts retrieval latency by 34 % with < 2 pp recall loss, and (ii) a two level summary of summaries eliminates cascade errors that otherwise emerge after 1,000 turns. By reconciling verbatim recall with semantic continuity, our architecture offers a practical path toward scalable, privacy aware conversational AI capable of engaging in months long dialogue without retraining the underlying model.

권호기사

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 목차
HEMA : a hippocampus-inspired extended memory architecture for long-context AI conversations Kwangseob Ahn, Yongjoo Song p. 1-7
Keypoint-based distortion correction and data augmentation for highangle license plate recognition Sehun Kim, Kyeongseok Jang, Dongwoo Lee, Kwangchul Son p. 9-15
(A) study on learning method for Korean speech data using limited computing resource JeHyung Tak, Kyuhyun Choi, Hyunsik Na, Minsung Kim p. 17-21
Performance comparisons of bio-inspired optimization algorithms for grid synchronization Min-A Jung, Yeonwoo Lee p. 23-29
Adaptive movement and formation coordinated control for flying ad-hoc networks (FANETs) in dynamic environments Sun-Kyoung Kang, Yeonwoo Lee p. 31-40

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차

권호

기사명 원문보기 기사목차
닫기