Cover Image

EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Suh, Heejae, Jeon, Yejin, Kang, Deokhyung, Park, Taehee, Min, Yejin, Lee, Gary Geunbae
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems
by: Lee, Jihyun, et al.
Published: (2026)

Multi-Level Attention Aggregation for Language-Agnostic Speaker Replication
by: Jeon, Yejin, et al.
Published: (2024)

Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations
by: Jeon, Yejin, et al.
Published: (2024)

Audio-Based Linguistic Feature Extraction for Enhancing Multi-lingual and Low-Resource Text-to-Speech
by: Kim, Youngjae, et al.
Published: (2024)

PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
by: Lee, Jihyun, et al.
Published: (2025)

Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation
by: Kang, Deokhyung, et al.
Published: (2025)

Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation
by: Jeon, Yejin, et al.
Published: (2024)

Difficulty-Controllable Cloze Question Distractor Generation
by: Kang, Seokhoon, et al.
Published: (2025)

Learning When to Translate for Multilingual Reasoning
by: Kang, Deokhyung, et al.
Published: (2026)

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
by: Kim, San, et al.
Published: (2025)

Facilitating Personalized TTS for Dysarthric Speakers Using Knowledge Anchoring and Curriculum Learning
by: Jeon, Yejin, et al.
Published: (2025)

PanicToCalm: A Proactive Counseling Agent for Panic Attacks
by: Lee, Jihyun, et al.
Published: (2025)

Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis
by: Jeon, Yejin, et al.
Published: (2025)

MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance
by: Kim, Subin, et al.
Published: (2025)

Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection
by: Park, Taehee, et al.
Published: (2025)

Denoising Table-Text Retrieval for Open-Domain Question Answering
by: Kang, Deokhyung, et al.
Published: (2024)

Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing
by: Kang, Deokhyung, et al.
Published: (2024)

Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model
by: Kim, Daehee, et al.
Published: (2024)

Self-Correcting Code Generation Using Small Language Models
by: Cho, Jeonghun, et al.
Published: (2025)

An Investigation Into Explainable Audio Hate Speech Detection
by: An, Jinmyeong, et al.
Published: (2024)

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
by: Kang, Deokhyung, et al.
Published: (2025)

GuRE:Generative Query REwriter for Legal Passage Retrieval
by: Kim, Daehee, et al.
Published: (2025)

Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring
by: Do, Heejin, et al.
Published: (2025)

Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models
by: Lee, Yejin, et al.
Published: (2026)

Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
by: Lee, Wonjun, et al.
Published: (2024)

Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
by: Lee, Jihyun, et al.
Published: (2024)

DiagESC: Dialogue Synthesis for Integrating Depression Diagnosis into Emotional Support Conversation
by: Seo, Seungyeon, et al.
Published: (2024)

Physics-constrained symbolic regression for discovering closed-form equations of multimodal water retention curves from experimental data
by: Kim, Yejin, et al.
Published: (2026)

Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
by: Kim, San, et al.
Published: (2024)

Multi-aspect Depression Severity Assessment via Inductive Dialogue System
by: Lee, Chaebin, et al.
Published: (2024)

DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues
by: Shin, Joonhyeok, et al.
Published: (2026)

CLIP-KOA: Enhancing Knee Osteoarthritis Diagnosis with Multi-Modal Learning and Symmetry-Aware Loss Functions
by: Jeong, Yejin, et al.
Published: (2025)

Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models
by: Kang, Jaehoon, et al.
Published: (2026)

Are Muscular Dystrophies Cholesterol‐Handling Diseases? Lessons From HMGCR Variants and Statin‐Associated Myopathies
by: Yejin Kang, et al.
Published: (2026)

Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking
by: Lee, Jihyun, et al.
Published: (2024)

P2VA: Converting Persona Descriptions into Voice Attributes for Fair and Controllable Text-to-Speech
by: Lee, Yejin, et al.
Published: (2025)

Enhancing Multi-Image Understanding through Delimiter Token Scaling
by: Lee, Minyoung, et al.
Published: (2026)

CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
by: Li, Mengfan, et al.
Published: (2026)

4bit-Quantization in Vector-Embedding for RAG
by: Jeong, Taehee
Published: (2025)

Adaptive Travel Behaviors During Crisis Waves: A Co‐Occurrence Network of Social Media Discourse
by: Yejin Lee, et al.
Published: (2026)