Towards trustworthy and aligned machine learning: A data-centric survey with causality perspectives

H Liu, M Chaudhary, H Wang - arxiv preprint arxiv:2307.16851, 2023 - arxiv.org
The trustworthiness of machine learning has emerged as a critical topic in the field,
encompassing various applications and research areas such as robustness, security …

Reasoning implicit sentiment with chain-of-thought prompting

H Fei, B Li, Q Liu, L Bing, F Li, TS Chua - arxiv preprint arxiv:2305.11255, 2023 - arxiv.org
While sentiment analysis systems try to determine the sentiment polarities of given targets
based on the key opinion expressions in input texts, in implicit sentiment analysis (ISA) the …

Causal intervention graph neural network for fault diagnosis of complex industrial processes

R Liu, Q Zhang, D Lin, W Zhang, SX Ding - Reliability Engineering & …, 2024 - Elsevier
With the development of industry and manufacturing, the mechanical structures of
equipment have become intricate and complex. Due to the interaction between components …

Rvisa: reasoning and verification for implicit sentiment analysis

W Lai, H **e, G Xu, Q Li - IEEE Transactions on Affective …, 2025 - ieeexplore.ieee.org
Under the context of the increasing social demand for fine-grained sentiment analysis (SA),
implicit sentiment analysis (ISA) poses a significant challenge owing to the absence of …

Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations

J Ouyang, Z Yang, S Liang, B Wang… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Aspect-based sentiment analysis (ABSA), a fine-grained sentiment classification task, has
received much attention recently. Many works investigate sentiment information through …

Aspect-category enhanced learning with a neural coherence model for implicit sentiment analysis

J Cui, F Fukumoto, X Wang, Y Suzuki… - Findings of the …, 2023 - aclanthology.org
Aspect-based sentiment analysis (ABSA) has been widely studied since the explosive
growth of social networking services. However, the recognition of implicit sentiments that do …

Aligning as Debiasing: Causality-Aware Alignment via Reinforcement Learning with Interventional Feedback

Y **a, T Yu, Z He, H Zhao, J McAuley… - Proceedings of the 2024 …, 2024 - aclanthology.org
Large language models (LLMs) often generate biased outputs containing offensive, toxic, or
stereotypical text. Existing LLM alignment methods such as reinforcement learning from …

Aspect-level implicit sentiment analysis model based on semantic wave and knowledge enhancement

M Zhang, F Wu, WL Chen, X Li - The Journal of Supercomputing, 2024 - Springer
Most implicit sentiment sentences in aspect level implicit sentiment analysis lack emotional
words, but there are still potential emotional clues. Current research mainly utilizes …

EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization

O Sotolar, V Formanek, A Debnath, A Lahnala… - arxiv preprint arxiv …, 2024 - arxiv.org
Empathetic response generation is a desirable aspect of conversational agents, crucial for
facilitating engaging and emotionally intelligent multi-turn conversations between humans …

Multi-task learning with llms for implicit sentiment analysis: Data-level and task-level automatic weight learning

W Lai, H **e, G Xu, Q Li - arxiv preprint arxiv:2412.09046, 2024 - arxiv.org
Implicit sentiment analysis (ISA) presents significant challenges due to the absence of
salient cue words. Previous methods have struggled with insufficient data and limited …