Efficient utilization of pre-trained models: A review of sentiment analysis via prompt learning

K Bu, Y Liu, X Ju - Knowledge-Based Systems, 2024 - Elsevier
Sentiment analysis is one of the traditional well-known tasks in Natural Language
Processing (NLP) research. In recent years, Pre-trained Models (PMs) have become one of …

Structured information extraction from scientific text with large language models

J Dagdelen, A Dunn, S Lee, N Walker… - Nature …, 2024 - nature.com
Extracting structured knowledge from scientific text remains a challenging task for machine
learning models. Here, we present a simple approach to joint named entity recognition and …

Contrastive learning reduces hallucination in conversations

W Sun, Z Shi, S Gao, P Ren, M de Rijke… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Pre-trained language models (LMs) store knowledge in their parameters and can generate
informative responses when used in conversational systems. However, LMs suffer from the …

State-of-the-art generalisation research in NLP: a taxonomy and review

D Hupkes, M Giulianelli, V Dankers, M Artetxe… - arxiv preprint arxiv …, 2022 - arxiv.org
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

Proactive Conversational AI: A Comprehensive Survey of Advancements and Opportunities

Y Deng, L Liao, W Lei, G Yang, W Lam… - ACM Transactions on …, 2025 - dl.acm.org
Dialogue systems are designed to offer human users social support or functional services
through natural language interactions. Traditional conversation research has put significant …

Honest students from untrusted teachers: Learning an interpretable question-answering pipeline from a pretrained language model

J Eisenstein, D Andor, B Bohnet, M Collins… - arxiv preprint arxiv …, 2022 - arxiv.org
Explainable question answering systems should produce not only accurate answers but
also rationales that justify their reasoning and allow humans to check their work. But what …

Thinksum: Probabilistic reasoning over sets using large language models

B Ozturkler, N Malkin, Z Wang, N Jojic - arxiv preprint arxiv:2210.01293, 2022 - arxiv.org
Large language models (LLMs) have a substantial capacity for high-level analogical
reasoning: reproducing patterns in linear text that occur in their training data (zero-shot …

Multi-source multi-type knowledge exploration and exploitation for dialogue generation

X Ni, H Dai, Z Ren, P Li - Proceedings of the 2023 Conference on …, 2023 - aclanthology.org
Open-domain multi-turn dialogue generation encounters the significant challenge of lacking
various types of knowledge from diverse sources. Existing models typically focus on …

Reprompting: Automated chain-of-thought prompt inference through gibbs sampling

W Xu, A Banburski-Fahey, N Jojic - arxiv preprint arxiv:2305.09993, 2023 - arxiv.org
We introduce Reprompting, an iterative sampling algorithm that searches for the Chain-of-
Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling …

Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning

X Yu, M Chen, Z Yu - arxiv preprint arxiv:2305.13660, 2023 - arxiv.org
Planning for goal-oriented dialogue often requires simulating future dialogue interactions
and estimating task progress. Many approaches thus consider training neural networks to …