Related papers: Discerning and Resolving Knowledge Conflicts throu…
Providing knowledge documents for large language models (LLMs) has emerged as a promising solution to update the static knowledge inherent in their parameters. However, knowledge in the document may conflict with the memory of LLMs due to…
Resolving knowledge conflicts is a crucial challenge in Question Answering (QA) tasks, as the internet contains numerous conflicting facts and opinions. While some research has made progress in tackling ambiguous settings where multiple…
Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity. This decoding method…
Large reasoning models have demonstrated remarkable performance on complex reasoning tasks, yet the excessive length of their chain-of-thought outputs remains a major practical bottleneck due to high computation cost and poor deployability.…
Large language models (LLMs) excel at a range of tasks through in-context learning (ICL), where only a few task examples guide their predictions. However, prior research highlights that LLMs often overlook input-label mapping information in…
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…
Multimodal large language models (MLLMs) have shown impressive capabilities in document understanding, a rapidly growing research area with significant industrial demand. As a multimodal task, document understanding requires models to…
Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by…
Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context. Such conflicts can lead to undesirable…
Large language models (LLMs) draw on both contextual information and parametric memory, yet these sources can conflict. Prior studies have largely examined this issue in contextual question answering, implicitly assuming that tasks should…
In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand…
This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt. Building on prior question-answering (QA) research, we…
Large Language Models (LLMs) encode vast world knowledge across multiple languages, yet their internal beliefs are often unevenly distributed across linguistic spaces. When external evidence contradicts these language-dependent memories,…
Although one-hot encoding is commonly used for multiclass classification, it is not always the most effective encoding mechanism. Error Correcting Output Codes (ECOC) address multiclass classification by mapping each class to a unique…
The open-set text recognition task is an emerging challenge that requires an extra capability to cognize novel characters during evaluation. We argue that a major cause of the limited performance for current methods is the confounding…
Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…
We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large language models. CoDeC distinguishes between data memorized during training and data outside…
Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. While model editing methods have been developed to address such errors without full re-training, they…
Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…
Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals. We formalize these failures under a unified notion of knowledge conflict, distinguishing…