17 citations · 103 across the 53 of their papers we have counts for
23 papers · 1 filter
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Le Yu, Bowen Yu, Haiyang Yu +2
In this paper, we unveil that Language Models (LMs) can acquire new capabilities by assimilating parameters from homologous models without retraining or GPUs. We first introduce DA…
Diversify Question Generation with Retrieval-Augmented Style Transfer
Qi Gou, Zehua Xia, Bowen Yu +4
Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems. E…
Improving Question Generation with Multi-level Content Planning
Zehua Xia, Qi Gou, Bowen Yu +4
This paper addresses the problem of generating questions from a given context and an answer, specifically focusing on questions that require multi-hop reasoning across an extended…
Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection
Yi Dai, Hao Lang, Kaisheng Zeng +2
Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution…
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…
VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue
Yunshui Li, Binyuan Hui, Zhaochao Yin +6
Visually-grounded dialog systems, which integrate multiple modes of communication such as text and visual inputs, have become an increasingly popular area of investigation. However…
Wider and Deeper LLM Networks are Fairer LLM Evaluators
Xinghua Zhang, Bowen Yu, Haiyang Yu +5
Measuring the quality of responses generated by LLMs is a challenging task, particularly when it comes to evaluating whether the response is aligned with human preference. A novel…
A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment
Yingxiu Zhao, Bowen Yu, Binyuan Hui +4
Training large language models (LLMs) with open-domain instruction data has yielded remarkable success in aligning to end tasks and human preferences. Extensive research has highli…
Unified Language Representation for Question Answering over Text, Tables, and Images
Bowen Yu, Cheng Fu, Haiyang Yu +2
When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data. Previous approaches to this problem have f…
Universal Information Extraction with Meta-Pretrained Self-Retrieval
Xin Cong. Bowen Yu, Mengcheng Fang, Tingwen Liu +5
Universal Information Extraction~(Universal IE) aims to solve different extraction tasks in a uniform text-to-structure generation manner. Such a generation procedure tends to stru…
PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
Yunshui Li, Binyuan Hui, ZhiChao Yin +3
Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach f…
Preference Ranking Optimization for Human Alignment
Feifan Song, Bowen Yu, Minghao Li +4
Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human f…
Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark
Yuxing Long, Binyuan Hui, Caixia Yuan1 +3
Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario…
Long-Tailed Question Answering in an Open World
Yi Dai, Hao Lang, Yinhe Zheng +2
Real-world data often have an open long-tailed distribution, and building a unified QA model supporting various tasks is vital for practical QA applications. However, it is non-tri…
Domain Incremental Lifelong Learning in an Open World
Yi Dai, Hao Lang, Yinhe Zheng +3
Lifelong learning (LL) is an important ability for NLP models to learn new tasks continuously. Architecture-based approaches are reported to be effective implementations for LL mod…
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…
Iterative Forward Tuning Boosts In-Context Learning in Language Models
Jiaxi Yang, Binyuan Hui, Min Yang +5
Despite the advancements in in-context learning (ICL) for large language models (LLMs), current research centers on specific prompt engineering, such as demonstration selection, wi…
Causal Document-Grounded Dialogue Pre-training
Yingxiu Zhao, Bowen Yu, Haiyang Yu +6
The goal of document-grounded dialogue (DocGD) is to generate a response by grounding the evidence in a supporting document in accordance with the dialogue context. This process in…
Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts
Hao Lang, Yinhe Zheng, Binyuan Hui +2
Out-of-Domain (OOD) intent detection is vital for practical dialogue systems, and it usually requires considering multi-turn dialogue contexts. However, most previous OOD intent de…
A Survey on Out-of-Distribution Detection in NLP
Hao Lang, Yinhe Zheng, Yixuan Li +3
Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of machine learning systems in the real world. Great progress has been made over the past year…
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
Minghao Li, Yingxiu Zhao, Bowen Yu +6
Recent research has demonstrated that Large Language Models (LLMs) can enhance their capabilities by utilizing external tools. However, three pivotal questions remain unanswered: (…
Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs
Yeqin Zhang, Haomin Fu, Cheng Fu +3
Multi-document grounded dialogue systems (DGDS) belong to a class of conversational agents that answer users' requests by finding supporting knowledge from a collection of document…
Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning
Yunhu Ye, Binyuan Hui, Min Yang +3
Table-based reasoning has shown remarkable progress in combining deep models with discrete reasoning, which requires reasoning over both free-form natural language (NL) questions a…