@inproceedings{reddy-etal-2025-simulating,
title = "Simulating Emotional Intelligence in {LLM}s through Behavioral Conditioning and Analogical Retrieval",
author = "Reddy, G.Sai Linisha and
Kankhara, Mounil Hiren and
Maheshwari, Mridul and
Bansal, Swayam and
Kapoor, Rishit and
M, Himesh Reddy and
Kumar, Bagesh",
editor = "Rambelli, Giulia and
Ilievski, Filip and
Bolognesi, Marianna and
Sommerauer, Pia",
booktitle = "Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.analogyangle-1.7/",
doi = "10.18653/v1/2025.analogyangle-1.7",
pages = "81--91",
ISBN = "979-8-89176-274-9",
abstract = "Human emotional expression emerges from a complex interplay of verbal, para-verbal, and non-verbal cues. This paper presents a dual-path framework for emotionally grounded text generation in large language models by integrating behavioral metadata with analogical retrieval. We introduce the MECC (Multimodal Emotionally Conditioned Corpus), a dataset of 1,764 question-answer pairs collected via structured interviews and annotated across 15 emotion categories with tone, response time, and body language. A LLaMA-3.1{--}8B{--}Instruct model is fine-tuned on MECC using behavior-encoded prompts, and inference is supported by a metadata-filtered Retrieval-Augmented Generation (RAG) pipeline. Detailed emotion-level analysis reveals trade-offs between emotional fidelity and semantic diversity, emphasizing the need for nuanced evaluation. This study contributes a richly annotated multimodal emotion corpus, a metadata-driven RAG architecture, a well-structured framework for building emotionally aware language models.Our code is available at https://github.com/MetaResearcher/Framework"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reddy-etal-2025-simulating">
<titleInfo>
<title>Simulating Emotional Intelligence in LLMs through Behavioral Conditioning and Analogical Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">G.Sai</namePart>
<namePart type="given">Linisha</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mounil</namePart>
<namePart type="given">Hiren</namePart>
<namePart type="family">Kankhara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mridul</namePart>
<namePart type="family">Maheshwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swayam</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishit</namePart>
<namePart type="family">Kapoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Himesh</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bagesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Rambelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Ilievski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Bolognesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pia</namePart>
<namePart type="family">Sommerauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-274-9</identifier>
</relatedItem>
<abstract>Human emotional expression emerges from a complex interplay of verbal, para-verbal, and non-verbal cues. This paper presents a dual-path framework for emotionally grounded text generation in large language models by integrating behavioral metadata with analogical retrieval. We introduce the MECC (Multimodal Emotionally Conditioned Corpus), a dataset of 1,764 question-answer pairs collected via structured interviews and annotated across 15 emotion categories with tone, response time, and body language. A LLaMA-3.1–8B–Instruct model is fine-tuned on MECC using behavior-encoded prompts, and inference is supported by a metadata-filtered Retrieval-Augmented Generation (RAG) pipeline. Detailed emotion-level analysis reveals trade-offs between emotional fidelity and semantic diversity, emphasizing the need for nuanced evaluation. This study contributes a richly annotated multimodal emotion corpus, a metadata-driven RAG architecture, a well-structured framework for building emotionally aware language models.Our code is available at https://github.com/MetaResearcher/Framework</abstract>
<identifier type="citekey">reddy-etal-2025-simulating</identifier>
<identifier type="doi">10.18653/v1/2025.analogyangle-1.7</identifier>
<location>
<url>https://aclanthology.org/2025.analogyangle-1.7/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>81</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simulating Emotional Intelligence in LLMs through Behavioral Conditioning and Analogical Retrieval
%A Reddy, G.Sai Linisha
%A Kankhara, Mounil Hiren
%A Maheshwari, Mridul
%A Bansal, Swayam
%A Kapoor, Rishit
%A M, Himesh Reddy
%A Kumar, Bagesh
%Y Rambelli, Giulia
%Y Ilievski, Filip
%Y Bolognesi, Marianna
%Y Sommerauer, Pia
%S Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-274-9
%F reddy-etal-2025-simulating
%X Human emotional expression emerges from a complex interplay of verbal, para-verbal, and non-verbal cues. This paper presents a dual-path framework for emotionally grounded text generation in large language models by integrating behavioral metadata with analogical retrieval. We introduce the MECC (Multimodal Emotionally Conditioned Corpus), a dataset of 1,764 question-answer pairs collected via structured interviews and annotated across 15 emotion categories with tone, response time, and body language. A LLaMA-3.1–8B–Instruct model is fine-tuned on MECC using behavior-encoded prompts, and inference is supported by a metadata-filtered Retrieval-Augmented Generation (RAG) pipeline. Detailed emotion-level analysis reveals trade-offs between emotional fidelity and semantic diversity, emphasizing the need for nuanced evaluation. This study contributes a richly annotated multimodal emotion corpus, a metadata-driven RAG architecture, a well-structured framework for building emotionally aware language models.Our code is available at https://github.com/MetaResearcher/Framework
%R 10.18653/v1/2025.analogyangle-1.7
%U https://aclanthology.org/2025.analogyangle-1.7/
%U https://doi.org/10.18653/v1/2025.analogyangle-1.7
%P 81-91
Markdown (Informal)
[Simulating Emotional Intelligence in LLMs through Behavioral Conditioning and Analogical Retrieval](https://aclanthology.org/2025.analogyangle-1.7/) (Reddy et al., Analogy-Angle 2025)
ACL
- G.Sai Linisha Reddy, Mounil Hiren Kankhara, Mridul Maheshwari, Swayam Bansal, Rishit Kapoor, Himesh Reddy M, and Bagesh Kumar. 2025. Simulating Emotional Intelligence in LLMs through Behavioral Conditioning and Analogical Retrieval. In Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II), pages 81–91, Vienna, Austria. Association for Computational Linguistics.