Towards a unified view of preference learning for large language models: A survey

B Gao, F Song, Y Miao, Z Cai, Z Yang, L Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial
factors to achieve success is aligning the LLM's output with human preferences. This …

Financial knowledge large language model

C Yang, C Xu, Y Qi - arxiv preprint arxiv:2407.00365, 2024 - arxiv.org
Artificial intelligence is making significant strides in the finance industry, revolutionizing how
data is processed and interpreted. Among these technologies, large language models …

FactAlign: Long-form factuality alignment of large language models

CW Huang, YN Chen - arxiv preprint arxiv:2410.01691, 2024 - arxiv.org
Large language models have demonstrated significant potential as the next-generation
information access engines. However, their reliability is hindered by issues of hallucination …

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization

Y Lyu, L Yan, Z Wang, D Yin, P Ren, M de Rijke… - arxiv preprint arxiv …, 2024 - arxiv.org
As large language models (LLMs) are rapidly advancing and achieving near-human
capabilities, aligning them with human values is becoming more urgent. In scenarios where …

Cognitive Biases in Large Language Models for News Recommendation

Y Lyu, X Zhang, Z Ren, M de Rijke - arxiv preprint arxiv:2410.02897, 2024 - arxiv.org
Despite large language models (LLMs) increasingly becoming important components of
news recommender systems, employing LLMs in such systems introduces new risks, such …

KEIR@ ECIR 2025: The Second Workshop on Knowledge-Enhanced Information Retrieval

Z Wang, J Fang, G Frisoni, Z Dai, Z Meng… - arxiv preprint arxiv …, 2025 - arxiv.org
Pretrained language models (PLMs) like BERT and GPT-4 have become the foundation for
modern information retrieval (IR) systems. However, existing PLM-based IR models primarily …