Related papers: Resolving Knowledge Conflicts in Domain-specific D…

Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate…

Although Large Language Models (LLMs) have demonstrated impressive text generation capabilities, they are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations. To alleviate LLMs…

Large language models (LLMs) are increasingly adopted in high-stakes domains such as healthcare and medical education, where the risk of generating factually incorrect (i.e., hallucinated) information is a major concern. While significant…

Clinical Decision Support Systems (CDSSs) provide reasoning and inquiry guidance for physicians, yet they face notable challenges, including high maintenance costs and low generalization capability. Recently, Large Language Models (LLMs)…

Large language models (LLMs) are commonly trained on multi-domain datasets, where domain sampling strategies significantly impact model performance due to varying domain importance across downstream tasks. Existing approaches for optimizing…

Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removing undesirable…

Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs. Previous efforts in detecting hallucinations have been employed at logit-level uncertainty estimation or language-level…

Large language models (LLMs) exhibit excellent performance in natural language processing (NLP), but remain highly sensitive to the quality of input queries, especially when these queries contain misleading or inaccurate information.…

Cross-domain Sequential Recommendation (CDSR) has been proposed to enrich user-item interactions by incorporating information from various domains. Despite current progress, the imbalance issue and transition issue hinder further…

Conventional knowledge distillation (KD) methods require access to the internal information of teachers, e.g., logits. However, such information may not always be accessible for large pre-trained language models (PLMs). In this work, we…

Detecting deceptive conversations on dynamic platforms is increasingly difficult due to evolving language patterns and Concept Drift (CD)-i.e., semantic or topical shifts that alter the context or intent of interactions over time. These…

This work investigates the selection of high-quality pre-training data from massive corpora to enhance LMs' capabilities for downstream usage. We formulate data selection as a generalized Optimal Control problem, which can be solved…

Knowledge Components (KCs) are foundational to adaptive learning systems, but their manual identification by domain experts is a significant bottleneck. While Large Language Models (LLMs) offer a promising avenue for automating this…

Event temporal reasoning aims at identifying the temporal relations between two or more events from narratives. However, knowledge conflicts arise when there is a mismatch between the actual temporal relations of events in the context and…

Recent methodologies utilizing synthetic datasets have aimed to address inconsistent hallucinations in large language models (LLMs); however,these approaches are primarily tailored to specific tasks, limiting their generalizability.…

Large Language Models (LLMs) still face challenges when dealing with complex reasoning tasks, often resulting in hallucinations, which limit the practical application of LLMs. To alleviate this issue, this paper proposes a new method that…

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of…

Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture-independent…

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major…