Search Results for author:
Found 19 papers, 8 papers with code
Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?
One key finding in psychology is that compared with irrelevant past experiences, recalling relevant ones can help humans better handle new tasks.
Lifelong Event Detection with Embedding Space Separation and Compaction
However, the simple combination of memory data and new-task samples can still result in substantial forgetting of previously acquired knowledge, which may occur due to the potential overlap between the feature distribution of new data and the previously learned embedding space.
How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library
With the rise of Large Language Models (LLMs) in recent years, new opportunities are emerging, but also new challenges, and contamination is quickly becoming critical.
Data Augmentation using LLMs: Data Perspectives, Learning Paradigms and Challenges
In the rapidly evolving field of machine learning (ML), data augmentation (DA) has emerged as a pivotal technique for enhancing model performance by diversifying training examples without the need for additional data collection.
Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing
Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation.
Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning
Fine-tuning is the primary methodology for tailoring pre-trained large language models to specific tasks.
Improving In-context Learning via Bidirectional Alignment
Large language models (LLMs) have shown impressive few-shot generalization on many tasks via in-context learning (ICL).
ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?
Upon its release in late 2022, ChatGPT has brought a seismic shift in the entire landscape of AI, both in research and commerce.
Lifelong Sequence Generation with Dynamic Module Expansion and Adaptation
Inspired by the learning paradigm of humans, we propose Dynamic Module Expansion and Adaptation (DMEA), which enables the model to dynamically determine the architecture for acquiring new knowledge based on task correlation and select the most similar previous tasks to facilitate adaptation to new tasks.
In-Context Learning with Iterative Demonstration Selection
The output reasoning path is then used to choose demonstrations that are prepended to the test sample for inference.
PromptSum: Parameter-Efficient Controllable Abstractive Summarization
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 promising results in language understanding tasks, especially in low-resource scenarios.
Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition
In this work, we investigate the noise-invariant visual modality to strengthen robustness of AVSR, which can adapt to any testing noises while without dependence on noisy training data, a. k. a., unsupervised noise adaptation.
Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
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 factual correctness.
Retrieving Multimodal Information for Augmented Generation: A Survey
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 interact with the world.
Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?
Despite this, PT has been shown to rely heavily on good initialization of the prompt embeddings.
Is ChatGPT a General-Purpose Natural Language Processing Task Solver?
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., without adaptation on downstream data.
Is GPT-3 a Good Data Annotator?
In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks.
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
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 and representative labeled data is often expensive and time-consuming.
LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5
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.
