Tag
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.