相关论文: PromptSum: Parameter-Efficient Controllable Abstra…

This paper describes the IUST NLP Lab submission to the Prompting Large Language Models as Explainable Metrics Shared Task at the Eval4NLP 2023 Workshop on Evaluation & Comparison of NLP Systems. We have proposed a zero-shot prompt-based…

In real-world scenarios, labeled samples for dialogue summarization are usually limited (i.e., few-shot) due to high annotation costs for high-quality dialogue summaries. To efficiently learn from few-shot samples, previous works have…

In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, effective persona integration remains a challenge. In this…

Controllable summarization aims to provide summaries that take into account user-specified aspects and preferences to better assist them with their information need, as opposed to the standard summarization setup which build a single…

Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central to guiding model outputs. While manual methods can be…

Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks…

Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increasing demand for fine-tuning a single LLM for multiple tasks because it requires overall…

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training…

Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language models (VLMs). This approach leverages task-specific instructions, known as prompts, to enhance…

Why can pre-trained language models (PLMs) learn universal representations and effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically find evidence indicating that the adaptations of PLMs to various…

Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities.…

Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks. However, it is still highly challenging to fully fine-tune these models for downstream tasks due to their high computational and…

Recently the prompt-tuning paradigm has attracted significant attention. By only tuning continuous prompts with a frozen pre-trained language model (PLM), prompt-tuning takes a step towards deploying a shared frozen PLM to serve numerous…

Transformer-based Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts. However, controlling the direction of generation via textual prompts has been challenging, especially…

Prompting has emerged as the dominant paradigm for adapting large, pre-trained transformer-based models to downstream tasks. The Prompting Decision Transformer (PDT) enables large-scale, multi-task offline Reinforcement Learning (RL)…

We introduce a simple but flexible mechanism to learn an intermediate plan to ground the generation of abstractive summaries. Specifically, we prepend (or prompt) target summaries with entity chains -- ordered sequences of entities…

Code summarization has emerged as a fundamental technique in the field of program comprehension. While code language models have shown significant advancements, the current models and benchmarks are confined to high-readability code, which…

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several…

Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-data scenario over…

Based on the remarkable achievements of pre-trained language models in abstractive summarization, the copying mechanism has proved helpful by improving the factuality, stability, and overall performance. This work proposes PROM, a new…