@inproceedings{soloshenko-etal-2025-personalizing,
title = "Personalizing chatbot communication with associative memory",
author = "Soloshenko, Kirill and
Shatalina, Alexandra and
Sevostyanova, Marina and
Kornilova, Elizaveta and
Zaitsev, Konstantin",
editor = "Velichkov, Boris and
Nikolova-Koleva, Ivelina and
Slavcheva, Milena",
booktitle = "Proceedings of the 9th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-stud.8/",
pages = "62--69",
abstract = "In our research paper we present the approach that is aimed at effectively expanding the context through integrating a database of associative memory into the pipeline. In order to improve long-term memory and personalization we have utilized methods close to Retrieval-Augmented Generation (RAG). Our method uses a multi-agent pipeline with a cold-start agent for initial interactions, a fact extraction agent to process user inputs, an associative memory agent for storing and retrieving context, and a generation agent for replying to user{'}s queries.Evaluation results show promising results: a 41{\%} accuracy improvement over the base Gemma3 model (from 16{\%} to 57{\%}). Hence, with our approach, we demonstrate that personalized chatbots can bypass LLM memory limitations while increasing information reliability under the conditions of limited context and memory."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soloshenko-etal-2025-personalizing">
<titleInfo>
<title>Personalizing chatbot communication with associative memory</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kirill</namePart>
<namePart type="family">Soloshenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Shatalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Sevostyanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizaveta</namePart>
<namePart type="family">Kornilova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Zaitsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Velichkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Nikolova-Koleva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Slavcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In our research paper we present the approach that is aimed at effectively expanding the context through integrating a database of associative memory into the pipeline. In order to improve long-term memory and personalization we have utilized methods close to Retrieval-Augmented Generation (RAG). Our method uses a multi-agent pipeline with a cold-start agent for initial interactions, a fact extraction agent to process user inputs, an associative memory agent for storing and retrieving context, and a generation agent for replying to user’s queries.Evaluation results show promising results: a 41% accuracy improvement over the base Gemma3 model (from 16% to 57%). Hence, with our approach, we demonstrate that personalized chatbots can bypass LLM memory limitations while increasing information reliability under the conditions of limited context and memory.</abstract>
<identifier type="citekey">soloshenko-etal-2025-personalizing</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-stud.8/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>62</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personalizing chatbot communication with associative memory
%A Soloshenko, Kirill
%A Shatalina, Alexandra
%A Sevostyanova, Marina
%A Kornilova, Elizaveta
%A Zaitsev, Konstantin
%Y Velichkov, Boris
%Y Nikolova-Koleva, Ivelina
%Y Slavcheva, Milena
%S Proceedings of the 9th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F soloshenko-etal-2025-personalizing
%X In our research paper we present the approach that is aimed at effectively expanding the context through integrating a database of associative memory into the pipeline. In order to improve long-term memory and personalization we have utilized methods close to Retrieval-Augmented Generation (RAG). Our method uses a multi-agent pipeline with a cold-start agent for initial interactions, a fact extraction agent to process user inputs, an associative memory agent for storing and retrieving context, and a generation agent for replying to user’s queries.Evaluation results show promising results: a 41% accuracy improvement over the base Gemma3 model (from 16% to 57%). Hence, with our approach, we demonstrate that personalized chatbots can bypass LLM memory limitations while increasing information reliability under the conditions of limited context and memory.
%U https://aclanthology.org/2025.ranlp-stud.8/
%P 62-69
Markdown (Informal)
[Personalizing chatbot communication with associative memory](https://aclanthology.org/2025.ranlp-stud.8/) (Soloshenko et al., RANLP 2025)
ACL
- Kirill Soloshenko, Alexandra Shatalina, Marina Sevostyanova, Elizaveta Kornilova, and Konstantin Zaitsev. 2025. Personalizing chatbot communication with associative memory. In Proceedings of the 9th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing, pages 62–69, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.