Challenge: Existing LLM-based conversational systems do not take into account the student’s affective states.
Approach: They propose an emotionally aware LLM-powered math tutor that models student emotions and maps them to relevant pedagogical strategies.
Outcome: The proposed model improves student engagement and learning effectiveness by 23 points using win rate and 3 points at an overall level using DAMR scores.

Similar Papers

LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight (2026.acl-long)

Copied to clipboard

Challenge: Emotional coordination is a core property of human interaction that shapes relational meaning . prior approaches treat sentiment as a deterministic point estimate for individual speakers . scalable and deployable approach extends beyond education to broader social and behavioral research .
Approach: They propose a probabilistic framework that characterizes emotion as a latent probability distribution defined over an affective space.
Outcome: The proposed framework characterizes emotion as a latent probability distribution defined over affective space.
The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth (2024.naacl-long)

Copied to clipboard

Challenge: Queer youth face increased mental health risks, such as depression, anxiety, and suicidal ideation.
Approach: They propose a scale that is inspired by psychological standards and expert input to evaluate LLM's interactions with queer-related content.
Outcome: The proposed scale outperforms human responses to queer-related content and outperformed LLMs in the qualitative and quantitative analysis.
Self-chats from Large Language Models Make Small Emotional Support Chatbot Better (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations.
Approach: They propose an iterative expansion framework to prompt large teacher model to curate an expansive emotion support dialogue dataset.
Outcome: The proposed model outperforms the teacher model in some cases . the proposed model is based on an iterative expansion framework and is available on github.com/pandazzh2020/ExTES.
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have shown excellent mastering of human language but struggle in real-world applications that require mathematical problem-solving.
Approach: They propose a pipeline to train a general Math-Critique model from the LLM itself to provide feedback signals and employ rejective fine-tuning and direct preference optimization over the Llm's own generations for data collection.
Outcome: The proposed pipeline outperforms existing LLMs that could be two times larger.
Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition (2024.lrec-main)

Copied to clipboard

Challenge: Existing models for multimodal Emotion Recognition in conversation (ERC) use text as the main modality for emotion recognition.
Approach: They propose a Directed Acyclic Graph (DAG) approach that integrates textual, acoustic, and visual features within a unified framework.
Outcome: The proposed model outperforms baseline models on the IEMOCAP and MELD datasets.
ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing speech-to-speech large language models rely on ASR transcription or use encoders to extract latent representations, weakening affective information and contextual coherence in multi-turn dialogues.
Approach: They propose a framework for speech-based empathetic response generation that captures turn-level affective states and dialogue-level emotional dynamics.
Outcome: The proposed framework outperforms baselines in automatic and human evaluations and remains robust across different Large Language Model (LLM) backbones.
Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems (2024.emnlp-main)

Copied to clipboard

Challenge: Existing large language models (LLMs) can be adopted as tutoring agents for math and language learning.
Approach: They propose a framework to construct profiles of different student groups by refining and integrating both cognitive and noncognitive aspects, and leverage LLMs for personality-aware student simulation in a language learning scenario.
Outcome: The proposed framework can construct profiles of different student groups by refining and integrating both cognitive and noncognitive aspects, and leverage LLMs for personality-aware student simulation in a language learning scenario.
Towards AI-Assisted Psychotherapy: Emotion-Guided Generative Interventions (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) lack rich non-verbal emotional cues essential to real-world therapy.
Approach: They propose a multimodal dataset of 1,441 publicly sourced therapy session videos containing both dialogue and non-verbal signals such as facial expressions and vocal tone.
Outcome: The proposed model improves the quality of generated interventions and evaluators misalign with expert assessments in this domain, highlighting the need for human-centered evaluation.
SoulChat: Improving LLMs’ Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are used in psychological counseling to provide universal advice.
Approach: They constructed a multi-turn empathetic conversation dataset with 2 million samples . they found that the model's empathy ability is enhanced when finetuning .
Outcome: Experiments show that large language models can be finetuned to provide empathy . but, when applied to mental health or emotional support conversation, there are three main issues .
MuSE: a Multimodal Dataset of Stressed Emotion (2020.lrec-1)

Copied to clipboard

Challenge: Existing studies on the effects of stress and emotion on the production and perception of emotion are understudied.
Approach: They propose to use a multimodal stressed emotion dataset to study the interplay between the presence of stress and expressions of affect.
Outcome: The proposed dataset combines emotion and stress classification with annotations for the emotional content of the recordings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations