Hexiang Tan, Wanli Yang, Junwei Zhang, Xin Chen, Rui Tang, Du Su, Jingang Wang, Yuanzhuo Wang, Fei Sun, Xueqi Cheng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Hexiang Tan, Fei Sun, Sha Liu, Du Su, Qi Cao, Xin Chen, Jingang Wang, Xunliang Cai, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Large language models (LLMs) have achieved remarkable progress across various domains, yet their tendency to generate hallucinations remains a critical barrier to their practical reliability.Confidence calibration addresses this challenge by aligning a model's confidence with its actual accuracy, improving self-evaluation and trustworthiness.However, traditional confidence calibration, operating at response level, are inadequate for long-form generation, which involve complex outputs composed of multiple atomic facts, each with varying confidence, correctness, and relevance to the query.To overcome this limitation, we propose a fact-level confidence calibration framework that evaluates and adjusts confidence at the granularity of individual facts, incorporating both relevance and correctness.This framework identifies finer-grained calibration discrepancies, reduces overconfidence, and reveals confidence variance.Based on this framework, we introduce CARE (Confidence-Aware Fact Correction), a method that leverages high-confidence facts to iteratively refine and correct low-confidence ones.Experimental results demonstrate that our CARE effectively improves the quality of generated content.Our code is available at this link.

While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts generated by LLMs and those retrieved from external sources.To investigate this, we formulate a systematic framework to identify whether LLMs' responses are attributed to either generated or retrieved contexts.To easily trace the origin of the response, we construct datasets with conflicting contexts, i.e., each question is paired with both generated and retrieved contexts, yet only one of them contains the correct answer.Our experiments reveal a significant bias in several LLMs (GPT-4/3.5 and Llama2) to favor generated contexts, even when they provide incorrect information.We further identify two key factors contributing to this bias: i) contexts generated by LLMs typically show greater similarity to the questions, increasing their likelihood of being selected; ii) the segmentation process used in retrieved contexts disrupts their completeness, thereby hindering their full utilization in LLMs.Our analysis enhances the understanding of how LLMs merge diverse contexts, offers valuable insights for advancing current LLM augmentation methods, and highlights the risk of generated misinformation for retrieval-augmented LLMs 1 .

As an complement of cloud computing, fog computing provides computing services with closer geographic distance and focuses on distributed computing. In this paper, we consider the bi-objective task scheduling problem with heterogeneous resources in a fog-cloud computing system. There are two minimization objectives: energy consumption and delay. We formulate a workload allocation problem model involving fog devices (FDs) and the cloud servers (CSs). The computing resources are heterogeneous on the energy consumption, processing capability and delay. An energy-aware greedy heuristic algorithm (EG) is developed to search for Pareto Front solutions. For the problem under discussed, Experimental results indicate that the proposal algorithm is effective and robust compared with the comparison algorithm.