dialogue-systems

Tag

Cards List
#dialogue-systems

S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling

arXiv cs.CL · yesterday Cached

S2Dialog introduces a framework for retrieving multimodal dialogues based on semantic and acoustic styles, using contrastive learning to enhance retrieval performance on the DailyTalk dataset.

0 favorites 0 likes
#dialogue-systems

Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations

arXiv cs.CL · 5d ago Cached

This paper introduces Preference Tree Optimization (PTO), a framework that generates preference data via look-ahead simulations to iteratively improve goal-oriented dialogue agents, with experiments showing gains in Motivational Interviewing settings.

0 favorites 0 likes
#dialogue-systems

Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation

Hugging Face Daily Papers · 2026-08-10 Cached

This paper introduces UserIDA, a method for controllable user simulation that separates interaction intent from language expression, achieving significantly higher intent accuracy and response quality than baselines on the LMSYS-USP benchmark.

0 favorites 0 likes
#dialogue-systems

M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models

arXiv cs.CL · 2026-08-03 Cached

M3-DuplexBench is a new multi-turn, multilingual, multidomain benchmark for evaluating full-duplex spoken dialogue systems, supporting English and Japanese across casual conversation and question answering domains.

0 favorites 0 likes
#dialogue-systems

Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection

arXiv cs.AI · 2026-07-29 Cached

This paper introduces DebtBench, the first persona-enriched benchmark for debt collection negotiation, and DebtGPT, a debt collection agent that jointly optimizes financial recovery and interaction experience. Experiments show most LLMs struggle in this realistic scenario, while DebtGPT matches GPT-4o performance.

0 favorites 0 likes
#dialogue-systems

CallBench: A Benchmark for Dual-Goal Coordination in Phone Call Assistants

arXiv cs.AI · 2026-07-28 Cached

CallBench is a Chinese benchmark for evaluating dual-goal coordination in phone call assistants, containing 50,000 multi-turn dialogues across six scenarios, with a preset-aware evaluation protocol covering semantic understanding, safety, and dialogue rhythm.

0 favorites 0 likes
#dialogue-systems

Dynamic Commonsense Coordination for Empathetic Response Generation

arXiv cs.CL · 2026-07-27 Cached

Proposes DCC, a dynamic commonsense coordination framework for empathetic response generation that integrates residual-based interaction, association-guided filtering, and iterative decoding, achieving improved emotion classification and response diversity over baselines.

0 favorites 0 likes
#dialogue-systems

Instruct-FD: Can Your Full-Duplex Speech System Follow Turn-Taking Instructions?

arXiv cs.CL · 2026-07-24 Cached

Introduces Instruct-FD, a benchmark for evaluating whether full-duplex speech systems can follow explicit turn-taking instructions. Results show the best model achieves only 64.4% adherence, highlighting a significant gap in instruction-following turn management.

0 favorites 0 likes
#dialogue-systems

Empathy as Predictive Misalignment Tolerance: A Co-Regulation Framework and the Regime Structure of Dialogue Repair

arXiv cs.AI · 2026-07-20 Cached

This paper reframes empathy in AI dialogue systems as 'predictive misalignment tolerance' and proposes an Interpretive Error Tolerance (IET) heuristic. Experiments reveal that dialogue repair has a regime-dependent structure, trading off discriminative fidelity for gist preservation under different noise levels.

0 favorites 0 likes
#dialogue-systems

TRACER: Early Failure Detection for Task-Oriented Dialogue

arXiv cs.CL · 2026-07-07 Cached

TRACER predicts whether a task-oriented dialogue will fail by analyzing partial conversations using belief-state changes and text representations, enabling early warning before full breakdown.

0 favorites 0 likes
#dialogue-systems

From Propositional to Perceptual Asymmetry: Extending Frictive Policy Optimization to Asymmetric Partial Information Dialogue

arXiv cs.CL · 2026-07-01 Cached

This paper extends Frictive Policy Optimization (FPO) to handle perceptual asymmetry in dialogue, where participants hold asymmetric partial information. It demonstrates that evaluating friction from each participant's perspective is more effective than omniscient access, and proposes annotation refinements for grounding states.

0 favorites 0 likes
#dialogue-systems

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

Hugging Face Daily Papers · 2026-06-30 Cached

This paper investigates a bias in vision-language models where they overestimate shared understanding in dialogue, confusing perceptual access with communicative grounding. The findings have implications for dialogue systems and VLM evaluation.

0 favorites 0 likes
#dialogue-systems

UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems

arXiv cs.CL · 2026-06-15 Cached

This paper proposes UP-NRPA, an online framework that integrates user portraits with nested rollout policy adaptation using large language models to dynamically customize dialogue strategies without offline training, achieving 100% success on multiple dialogue tasks.

0 favorites 0 likes
#dialogue-systems

HyPE: Category-Aware Hypergraph Encoding with Persistent Edge Embeddings for Persona-Grounded Dialogue

arXiv cs.CL · 2026-06-12 Cached

HyPE introduces a hypergraph-based persona encoder that models high-order relations among persona attributes via category-aware hyperedges and persistent edge embeddings, achieving consistent improvements over flat pooling baselines on PersonaChat across multiple backbone models.

0 favorites 0 likes
#dialogue-systems

Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues

arXiv cs.CL · 2026-06-04 Cached

This paper introduces Fine-grained Fragment Retrieval (FFR), a new task for locating semantically coherent multi-modal fragments (text and images) within long-form dialogues. The authors propose F2RVLM, a generation-based retrieval model trained with reinforcement learning, and FFRS, a two-stage retrieval system, along with a new dataset MLDR for evaluation.

0 favorites 0 likes
#dialogue-systems

Memory Retrieval for Changing Preferences

arXiv cs.CL · 2026-06-03 Cached

This paper proposes a unified framework for memory access and selection in long-context dialogue systems, using Bayes factors to quantify the utility of historical turns for modeling changing user preferences. Experiments show it outperforms embedding-based retrieval on preference-intensive tasks.

0 favorites 0 likes
#dialogue-systems

Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation

arXiv cs.CL · 2026-05-26 Cached

This paper proposes PUMA, a framework for LLM personalization in multi-turn conversations that models latent user states and uses the Free Energy Principle to select dialogue actions, improving long-horizon outcomes on healthcare counseling benchmarks.

0 favorites 0 likes
#dialogue-systems

Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues

arXiv cs.CL · 2026-05-21 Cached

Proposes FF-BPSN, a forward-focused bidirectional pseudo-siamese network using two transformer decoders for dialogue path planning in target-oriented proactive dialogues, achieving state-of-the-art on DuRecDial benchmarks.

0 favorites 0 likes
#dialogue-systems

SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs

arXiv cs.CL · 2026-05-19 Cached

Proposes SKG-Eval, a quasi-deterministic evaluation framework for multi-turn dialogue that uses incremental semantic knowledge graphs to detect cross-turn inconsistencies, contradiction, and topic drift, achieving higher correlation with human judgments.

0 favorites 0 likes
#dialogue-systems

Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents

arXiv cs.CL · 2026-05-15 Cached

Introduces Inquisitive Conversational Agents (ICAs) for proactive information extraction in legal dialogue, proposing a Dual Hierarchical Reinforcement Learning framework that learns when and how to ask probing questions, evaluated on U.S. Supreme Court oral arguments.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback