相关论文: DZ-TDPO: Non-Destructive Temporal Alignment for Mu…

Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on local token likelihoods or scalar scores. We view generation as tracing a semantic…

Zero-shot Dialog State Tracking (zs-DST) is essential for enabling Task-Oriented Dialog Systems (TODs) to generalize to new domains without costly data annotation. A central challenge lies in the semantic misalignment between dynamic dialog…

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Tracking the state of the conversation is a central component in task-oriented spoken dialogue systems. One such approach for tracking the dialogue state is slot carryover, where a model makes a binary decision if a slot from the context is…

Recent advancements in open-domain dialogue systems have been propelled by the emergence of high-quality large language models (LLMs) and various effective training methodologies. Nevertheless, the presence of toxicity within these models…

Large Language Models (LLMs) struggle with information forgetting and inefficiency in long-horizon, multi-turn dialogues. To address this, we propose a training-free prompt engineering method, the State-Update Multi-turn Dialogue Strategy.…

Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations. Recent state-of-the-art DST implementations rely on schemata of diverse services to improve model robustness and handle…

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust…

Time series with long-term structure arise in a variety of contexts and capturing this temporal structure is a critical challenge in time series analysis for both inference and forecasting settings. Traditionally, state space models have…

In task-oriented dialogue systems the dialogue state tracker (DST) component is responsible for predicting the state of the dialogue based on the dialogue history. Current DST approaches rely on a predefined domain ontology, a fact that…

Dialog state tracking is used to estimate the current belief state of a dialog given all the preceding conversation. Machine reading comprehension, on the other hand, focuses on building systems that read passages of text and answer…

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with…

Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests.…

Effective information seeking in multi-turn medical dialogues is critical for accurate diagnosis, especially when dealing with incomplete information. Aligning Large Language Models (LLMs) for these interactive scenarios is challenging due…

Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations: over-reliance on pre-collected user data, and short-horizon biases in reinforcement…

Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information. While alignment techniques help LLMs align with human intentions and values, improving context-faithfulness through…

Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line, while non-autoregressive end to end TTS models rely on…

The latency-quality tradeoff is a fundamental constraint in open-domain dialogue AI systems, since comprehensive knowledge access necessitates prohibitive response delays. Contemporary approaches offer two inadequate solutions: lightweight…

Our goal is to enable large language models (LLMs) to balance multiple human preference dimensions; such as helpfulness, safety, and verbosity, through principled and controllable alignment. Existing preference optimization methods,…

This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3)…