QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism
- URL: http://arxiv.org/abs/2406.13167v1
- Date: Wed, 19 Jun 2024 02:46:18 GMT
- Title: QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism
- Authors: Bo Wang, Heyan Huang, Yixin Cao, Jiahao Ying, Wei Tang, Chong Feng,
- Abstract summary: Memory mechanism offers a flexible solution for managing long contexts.
We introduce a novel strategy, Question then Reflection Memory Mechanism (QRMeM), incorporating a dual-structured memory pool.
Our evaluation across multiple-choice questions (MCQ) and multi-document question answering (Multi-doc QA) benchmarks showcases QRMeM enhanced performance compared to existing approaches.
- Score: 46.441032033076034
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanism offers a flexible solution for managing long contexts, utilizing techniques such as compression, summarization, and structuring to facilitate nuanced and efficient handling of large volumes of text. However, existing techniques face challenges with static knowledge integration, leading to insufficient adaptation to task-specific needs and missing multi-segmentation relationships, which hinders the dynamic reorganization and logical combination of relevant segments during the response process. To address these issues, we introduce a novel strategy, Question then Reflection Memory Mechanism (QRMeM), incorporating a dual-structured memory pool. This pool synergizes static textual content with structured graph guidance, fostering a reflective trial-and-error approach for navigating and identifying relevant segments. Our evaluation across multiple-choice questions (MCQ) and multi-document question answering (Multi-doc QA) benchmarks showcases QRMeM enhanced performance compared to existing approaches.
Related papers
- Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach [6.549143816134531]
We propose a novel iterative RAG method called ReSP, equipped with a dual-function summarizer.
Experimental results on the multi-hop question-answering HotpotQA and 2WikiMultihopQA demonstrate that our method significantly outperforms the state-of-the-art.
arXiv Detail & Related papers (2024-07-18T02:19:00Z) - LaSagnA: Language-based Segmentation Assistant for Complex Queries [39.620806493454616]
Large Language Models for Vision (vLLMs) generate detailed perceptual outcomes, including bounding boxes and masks.
In this study, we acknowledge that the main cause of these problems is the insufficient complexity of training queries.
We present three novel strategies to effectively handle the challenges arising from the direct integration of the proposed format.
arXiv Detail & Related papers (2024-04-12T14:40:45Z) - Enhancing Textbook Question Answering Task with Large Language Models
and Retrieval Augmented Generation [3.948068081583197]
This paper proposes a methodology that handle the out-of-domain scenario in Textbook question answering (TQA)
Through supervised fine-tuning of the LLM model Llama-2 and the incorporation of RAG, our architecture outperforms the baseline, achieving a 4.12% accuracy improvement on validation set and 9.84% on test set for non-diagram multiple-choice questions.
arXiv Detail & Related papers (2024-02-05T11:58:56Z) - Thread of Thought Unraveling Chaotic Contexts [133.24935874034782]
"Thread of Thought" (ThoT) strategy draws inspiration from human cognitive processes.
In experiments, ThoT significantly improves reasoning performance compared to other prompting techniques.
arXiv Detail & Related papers (2023-11-15T06:54:44Z) - Walking Down the Memory Maze: Beyond Context Limit through Interactive
Reading [63.93888816206071]
We introduce MemWalker, a method that processes the long context into a tree of summary nodes. Upon receiving a query, the model navigates this tree in search of relevant information, and responds once it gathers sufficient information.
We show that, beyond effective reading, MemWalker enhances explainability by highlighting the reasoning steps as it interactively reads the text; pinpointing the relevant text segments related to the query.
arXiv Detail & Related papers (2023-10-08T06:18:14Z) - HPE:Answering Complex Questions over Text by Hybrid Question Parsing and
Execution [92.69684305578957]
We propose a framework of question parsing and execution on textual QA.
The proposed framework can be viewed as a top-down question parsing followed by a bottom-up answer backtracking.
Our experiments on MuSiQue, 2WikiQA, HotpotQA, and NQ show that the proposed parsing and hybrid execution framework outperforms existing approaches in supervised, few-shot, and zero-shot settings.
arXiv Detail & Related papers (2023-05-12T22:37:06Z) - Enhancing Large Language Model with Self-Controlled Memory Framework [56.38025154501917]
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.
We propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information.
arXiv Detail & Related papers (2023-04-26T07:25:31Z) - Semantics-Aware Dynamic Localization and Refinement for Referring Image
Segmentation [102.25240608024063]
Referring image segments an image from a language expression.
We develop an algorithm that shifts from being localization-centric to segmentation-language.
Compared to its counterparts, our method is more versatile yet effective.
arXiv Detail & Related papers (2023-03-11T08:42:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.