Related papers: Information Gain-Guided Causal Intervention for Au…
Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations. An over-reliance on linguistic priors has been identified…
Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…
The extraction of lung lesion information from clinical and medical imaging reports is crucial for research on and clinical care of lung-related diseases. Large language models (LLMs) can be effective at interpreting unstructured text in…
Identifying bias in LLMs is ongoing. Because they are still in development, what is true today may be false tomorrow. We therefore need general strategies for debiasing that will outlive current models. Strategies developed for debiasing…
Inductive Logic Programming (ILP) is a principled approach for generalizing regularities from data and constructing hypotheses as interpretable logic programs. However, a key limitation is its reliance on expert-crafted language bias - the…
Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts,…
Causal discovery (CD) and Large Language Models (LLMs) have emerged as transformative fields in artificial intelligence that have evolved largely independently. While CD specializes in uncovering cause-effect relationships from data, and…
Large Language Models (LLMs) are increasingly being deployed as the reasoning engines for agentic AI systems, yet they exhibit a critical flaw: a rigid adherence to explicit rules that leads to decisions misaligned with human common sense…
Large Language Models (LLMs) have demonstrated their capabilities across various tasks, from language translation to complex reasoning. Understanding and predicting human behavior and biases are crucial for artificial intelligence (AI)…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…
As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely…
Large Language Models~(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in…
We study how training data contributes to the emergence of toxic behaviors in large language models. Most prior work on reducing model toxicity adopts reactive approaches, such as fine-tuning pre-trained (and potentially toxic) models to…
Predictive models often need to work with incomplete information in real-world tasks. Consequently, they must provide reliable probability or confidence estimation, especially in large-scale decision-making and planning tasks. Current large…
Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue…
Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…
Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation…
Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parameter updates, yet its theoretical role remains poorly…
Despite the remarkable advancements in Visual Question Answering (VQA), the challenge of mitigating the language bias introduced by textual information remains unresolved. Previous approaches capture language bias from a coarse-grained…
Large Vision-Language Models (LVLMs) are increasingly adept at generating contextually detailed and coherent responses from visual inputs. However, their application in multimodal decision-making and open-ended generation is hindered by a…