English
Related papers

Related papers: DZ-TDPO: Non-Destructive Temporal Alignment for Mu…

200 papers

AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the…

Computation and Language · Computer Science 2025-05-27 Abhijnan Nath , Carine Graff , Andrei Bachinin , Nikhil Krishnaswamy

We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to…

Computation and Language · Computer Science 2021-09-30 Dingmin Wang , Chenghua Lin , Qi Liu , Kam-Fai Wong

Dialogue state tracking is the core part of a spoken dialogue system. It estimates the beliefs of possible user's goals at every dialogue turn. However, for most current approaches, it's difficult to scale to large dialogue domains. They…

Computation and Language · Computer Science 2018-10-24 Liliang Ren , Kaige Xie , Lu Chen , Kai Yu

This paper describes our approach to DSTC 9 Track 2: Cross-lingual Multi-domain Dialog State Tracking, the task goal is to build a Cross-lingual dialog state tracker with a training set in rich resource language and a testing set in low…

Computation and Language · Computer Science 2021-07-01 Min Mao , Jiasheng Liu , Jingyao Zhou , Haipang Wu

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…

Machine Learning · Computer Science 2025-11-20 Ranfei Chen , Ming Chen , Kaifei Wang

Generating spoken dialogue is inherently more complex than monologue text-to-speech (TTS), as it demands both realistic turn-taking and the maintenance of distinct speaker timbres. While existing autoregressive (AR) models have made…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-15 Han Zhu , Wei Kang , Liyong Guo , Zengwei Yao , Fangjun Kuang , Weiji Zhuang , Zhaoqing Li , Zhifeng Han , Dong Zhang , Xin Zhang , Xingchen Song , Lingxuan Ye , Long Lin , Daniel Povey

Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, we identify and…

Machine Learning · Computer Science 2025-12-12 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino , Paolo Mori

Recent advances in Large Language Models (LLMs) have transformed text-to-speech (TTS) synthesis, inspiring autoregressive frameworks that represent speech as sequences of discrete codec tokens. Among them, single-codebook TTS LLMs have…

Sound · Computer Science 2025-11-27 Yicheng Zhong , Peiji Yang , Zhisheng Wang

In-context learning with Large Language Models (LLMs) has emerged as a promising avenue of research in Dialog State Tracking (DST). However, the best-performing in-context learning methods involve retrieving and adding similar examples to…

Computation and Language · Computer Science 2024-02-06 Atharva Kulkarni , Bo-Hsiang Tseng , Joel Ruben Antony Moniz , Dhivya Piraviperumal , Hong Yu , Shruti Bhargava

Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach…

Computation and Language · Computer Science 2025-10-15 Yukun Zhang , Qi Dong

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Yang Li , Xinyu Fang , Shengyuan Ding , Peiji Li , Yongkang Chen , Yichuan Ma , Tianyi Lyu , Linyang Li , Dahua Lin , Qipeng Guo , Qingwen Liu , Kai Chen

We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction. It is based on a large language model (LLM) carefully aligned to be aware of a perception module, a motor function…

Computation and Language · Computer Science 2024-10-30 Peng Wang , Songshuo Lu , Yaohua Tang , Sijie Yan , Wei Xia , Yuanjun Xiong

In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. Drawing on Cognitive Load Theory…

Machine Learning · Computer Science 2026-03-06 Huayang Li , Tianyu Zhao , Deng Cai , Richard Sproat

Although there have been remarkable advances in dialogue systems through the dialogue systems technology competition (DSTC), it remains one of the key challenges to building a robust task-oriented dialogue system with a speech interface.…

Computation and Language · Computer Science 2024-01-10 Jaeseok Yoon , Seunghyun Hwang , Ran Han , Jeonguk Bang , Kee-Eung Kim

Generative inference in Large Language Models (LLMs) is impeded by the growing memory demands of Key-Value (KV) cache, especially for longer sequences. Traditional KV cache eviction strategies, which discard less critical KV pairs based on…

Computation and Language · Computer Science 2025-03-14 Zhongwei Wan , Xinjian Wu , Yu Zhang , Yi Xin , Chaofan Tao , Zhihong Zhu , Xin Wang , Siqi Luo , Jing Xiong , Longyue Wang , Mi Zhang

In this paper, we present a policy gradient method that avoids exploratory noise injection and performs policy search over the deterministic landscape. By avoiding noise injection all sources of estimation variance can be eliminated in…

Artificial Intelligence · Computer Science 2022-06-01 Ehsan Saleh , Saba Ghaffari , Timothy Bretl , Matthew West

Despite the fact that offline methods for Large Language Models (LLMs) alignment do not require a direct reward model, they remain susceptible to overoptimization. This issue arises when the trained model deviates excessively from the…

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Machine Learning · Computer Science 2026-02-24 Yuchen Zhu , Wei Guo , Jaemoo Choi , Petr Molodyk , Bo Yuan , Molei Tao , Yongxin Chen

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a…

Computation and Language · Computer Science 2025-06-05 Xiaofeng Zhou , Heyan Huang , Lizi Liao

Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known as language confusion. Prior mitigation approaches based on…

Computation and Language · Computer Science 2026-04-30 Jinho Choo , JunSeung Lee , Jimyeong Kim , Yeeho Song , S. K. Hong , Yeong-Dae Kwon