96 citations · 297 across the 21 of their papers we have counts for
21 papers
Supervised Optimism Correction: Be Confident When LLMs Are Sure
Junjie Zhang, Rushuai Yang, Shunyu Liu +5
In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing…
A Survey of Direct Preference Optimization
Shunyu Liu, Wenkai Fang, Zetian Hu +9
Large Language Models (LLMs) have demonstrated unprecedented generative capabilities, yet their alignment with human values remains critical for ensuring helpful and harmless deplo…
A Survey on Self-Evolution of Large Language Models
Zhengwei Tao, Ting-En Lin, Xiancai Chen +7
Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. However, current LLMs that learn from human or external model supervi…
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
Changyu Chen, Xiting Wang, Ting-En Lin +6
In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approach…
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
Yuhan Chen, Ang Lv, Ting-En Lin +5
In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demandi…
Constructive Large Language Models Alignment with Diverse Feedback
Tianshu Yu, Ting-En Lin, Yuchuan Wu +3
In recent research on large language models (LLMs), there has been a growing emphasis on aligning these models with human values to reduce the impact of harmful content. However, c…
Improving Factual Consistency of News Summarization by Contrastive Preference Optimization
Huawen Feng, Yan Fan, Xiong Liu +6
Despite the recent progress in news summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known…
Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Haoyu Gao, Ting-En Lin, Hangyu Li +4
Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these…
UniSA: Unified Generative Framework for Sentiment Analysis
Zaijing Li, Ting-En Lin, Yuchuan Wu +4
Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information. It consists of several subt…
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Tianshu Yu, Haoyu Gao, Ting-En Lin +6
Recently, speech-text pre-training methods have shown remarkable success in many speech and natural language processing tasks. However, most previous pre-trained models are usually…
Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Haoyu Gao, Rui Wang, Ting-En Lin +4
Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks. Previous DTS methods either focus on semantic similarity or dialogue coherence to…
SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
Shuzheng Si, Wentao Ma, Haoyu Gao +7
Task-oriented dialogue (TOD) models have made significant progress in recent years. However, previous studies primarily focus on datasets written by annotators, which has resulted…
Empathetic Response Generation via Emotion Cause Transition Graph
Yushan Qian, Bo Wang, Ting-En Lin +6
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e.g., emotion status) and cognitive factors (e.g., cause of the emotion). Besid…
UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition
Guimin Hu, Ting-En Lin, Yi Zhao +3
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspect…
Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems
Ting-En Lin, Yuchuan Wu, Fei Huang +3
In this paper, we present Duplex Conversation, a multi-turn, multimodal spoken dialogue system that enables telephone-based agents to interact with customers like a human. We use t…
Multi-View Active Fine-Grained Recognition
Ruoyi Du, Wenqing Yu, Heqing Wang +4
As fine-grained visual classification (FGVC) being developed for decades, great works related have exposed a key direction -- finding discriminative local regions and revealing sub…
Deep Open Intent Classification with Adaptive Decision Boundary
Hanlei Zhang, Hua Xu, Ting-En Lin
Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to d…
Discovering New Intents with Deep Aligned Clustering
Hanlei Zhang, Hua Xu, Ting-En Lin +1
Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also ha…
A Post-processing Method for Detecting Unknown Intent of Dialogue System via Pre-trained Deep Neural Network Classifier
Ting-En Lin, Hua Xu
With the maturity and popularity of dialogue systems, detecting user's unknown intent in dialogue systems has become an important task. It is also one of the most challenging tasks…
Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement
Ting-En Lin, Hua Xu, Hanlei Zhang
Identifying new user intents is an essential task in the dialogue system. However, it is hard to get satisfying clustering results since the definition of intents is strongly guide…
Deep Unknown Intent Detection with Margin Loss
Ting-En Lin, Hua Xu
Identifying the unknown (novel) user intents that have never appeared in the training set is a challenging task in the dialogue system. In this paper, we present a two-stage method…