62 citations · 160 across the 22 of their papers we have counts for
22 papers
Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation
Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman +10
Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation.…
A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
Zixuan Ke, Fangkai Jiao, Yifei Ming +9
Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making. With the rapid advancement of large language models (LLMs), reaso…
StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs
Hailin Chen, Fangkai Jiao, Mathieu Ravaut +8
The rapid advancement of large language models (LLMs) demands robust, unbiased, and scalable evaluation methods. However, human annotations are costly to scale, model-based evaluat…
Lifelong Event Detection with Embedding Space Separation and Compaction
Chengwei Qin, Ruirui Chen, Ruochen Zhao +2
To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, t…
Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?
Chengwei Qin, Wenhan Xia, Tan Wang +5
Analogical reasoning is a unique ability of humans to address unfamiliar challenges by transferring strategies from relevant past experiences. One key finding in psychology is that…
A Comprehensive Survey of Contamination Detection Methods in Large Language Models
Mathieu Ravaut, Bosheng Ding, Fangkai Jiao +6
With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming criti…
Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges
Bosheng Ding, Chengwei Qin, Ruochen Zhao +7
In the rapidly evolving field of large language models (LLMs), data augmentation (DA) has emerged as a pivotal technique for enhancing model performance by diversifying training ex…
Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing
Fangkai Jiao, Chengwei Qin, Zhengyuan Liu +2
Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation. However, recent studies have rai…
Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning
Wenhan Xia, Chengwei Qin, Elad Hazan
Fine-tuning is the primary methodology for tailoring pre-trained large language models to specific tasks. As the model's scale and the diversity of tasks expand, parameter-efficien…
Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning
Chengwei Qin, Wenhan Xia, Fangkai Jiao +5
Large language models (LLMs) have shown impressive few-shot generalization on many tasks via in-context learning (ICL). Despite their success in showing such emergent abilities, th…
Lifelong Sequence Generation with Dynamic Module Expansion and Adaptation
Chengwei Qin, Chen Chen, Shafiq Joty
Lifelong sequence generation (LSG), a problem in continual learning, aims to continually train a model on a sequence of generation tasks to learn constantly emerging new generation…
ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?
Hailin Chen, Fangkai Jiao, Xingxuan Li +5
Upon its release in late 2022, ChatGPT has brought a seismic shift in the entire landscape of AI, both in research and commerce. Through instruction-tuning a large language model (…
In-Context Learning with Iterative Demonstration Selection
Chengwei Qin, Aston Zhang, Chen Chen +2
Spurred by advancements in scale, large language models (LLMs) have demonstrated strong few-shot learning ability via in-context learning (ICL). However, the performance of ICL has…
PromptSum: Parameter-Efficient Controllable Abstractive Summarization
Mathieu Ravaut, Hailin Chen, Ruochen Zhao +3
Prompt tuning (PT), a parameter-efficient technique that only tunes the additional prompt embeddings while keeping the backbone pre-trained language model (PLM) frozen, has shown p…
Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition
Yuchen Hu, Ruizhe Li, Chen Chen +3
Audio-visual speech recognition (AVSR) provides a promising solution to ameliorate the noise-robustness of audio-only speech recognition with visual information. However, most exis…
Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
Ruochen Zhao, Xingxuan Li, Shafiq Joty +2
As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of fa…
Retrieving Multimodal Information for Augmented Generation: A Survey
Ruochen Zhao, Hailin Chen, Weishi Wang +8
As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs' generation ability, which enables LLMs to better intera…
Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?
Chengwei Qin, Qian Li, Ruochen Zhao +1
Prompt tuning (PT) which only tunes the embeddings of an additional sequence of tokens per task, keeping the pre-trained language model (PLM) frozen, has shown remarkable performan…
Is ChatGPT a General-Purpose Natural Language Processing Task Solver?
Chengwei Qin, Aston Zhang, Zhuosheng Zhang +3
Spurred by advancements in scale, large language models (LLMs) have demonstrated the ability to perform a variety of natural language processing (NLP) tasks zero-shot -- i.e., with…
Is GPT-3 a Good Data Annotator?
Bosheng Ding, Chengwei Qin, Linlin Liu +4
Data annotation is the process of labeling data that could be used to train machine learning models. Having high-quality annotation is crucial, as it allows the model to learn the…
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
Chengwei Qin, Shafiq Joty
Existing continual relation learning (CRL) methods rely on plenty of labeled training data for learning a new task, which can be hard to acquire in real scenario as getting large a…
LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5
Chengwei Qin, Shafiq Joty
Existing approaches to lifelong language learning rely on plenty of labeled data for learning a new task, which is hard to obtain in most real scenarios. Considering that humans ca…