Related papers: Discerning and Resolving Knowledge Conflicts throu…

Standard Large Language Model (LLM) pre-training typically treats corpora as flattened token sequences, often overlooking the real-world context that humans naturally rely on to contextualize information. To bridge this gap, we introduce…

While Chain-of-Thought (CoT) reasoning improves model performance, it incurs significant time costs due to the generation of discrete CoT tokens (DCoT). Continuous CoT (CCoT) offers a more efficient alternative, but existing CCoT methods…

Vision-Language Models (VLMs) exhibit strong performance in instruction following and open-ended vision-language reasoning, yet they frequently generate fluent outputs that are weakly grounded in visual evidence. Prior works have shown that…

The massive growth in the utilization of edge AI has made the applications of machine learning models ubiquitous in different domains. Despite the computation and communication efficiency of these systems, due to limited computation…

It is widely acknowledged that large language models (LLMs) encode a vast reservoir of knowledge after being trained on mass data. Recent studies disclose knowledge conflicts in LLM generation, wherein outdated or incorrect parametric…

Large language models (LLMs) enable in-context learning (ICL) by conditioning on a few labeled training examples as a text-based prompt, eliminating the need for parameter updates and achieving competitive performance. In this paper, we…

Context-aware neural machine translation (NMT) incorporates contextual information of surrounding texts, that can improve the translation quality of document-level machine translation. Many existing works on context-aware NMT have focused…

By providing external information to large language models (LLMs), tool augmentation (including retrieval augmentation) has emerged as a promising solution for addressing the limitations of LLMs' static parametric memory. However, how…

How do language models use contextual information to answer health questions? How are their responses impacted by conflicting contexts? We assess the ability of language models to reason over long, conflicting biomedical contexts using…

Large language models (LLMs) encode vast amounts of knowledge during pre-training (parametric knowledge, or PK) and can further be enhanced by incorporating contextual knowledge (CK). Can LLMs effectively integrate their internal PK with…

Large language models (LLMs) have achieved remarkable success across a wide range of applications especially when augmented by external knowledge through retrieval-augmented generation (RAG). Despite their widespread adoption, recent…

We present chain-of-knowledge (CoK), a novel framework that augments large language models (LLMs) by dynamically incorporating grounding information from heterogeneous sources. It results in more factual rationales and reduced hallucination…

Resolving conflicts is critical for improving the reliability of multi-view classification. While prior work focuses on learning consistent and informative representations across views, it often assumes perfect alignment and equal…

Large language models (LLMs) achieve remarkable generative performance, yet their output quality is dependent on the decoding strategy. While sampling-based methods (e.g., top-k, nucleus) and search-and-select based methods (e.g., beam…

Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrieval-based dialogue systems have paid tremendous efforts to utilize neural networks to build a matching model, where…

The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed several challenges. However, they still struggle with…

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without weight updates by learning from demonstration sequences. While ICL shows strong empirical performance, its internal representational mechanisms are…

Large language models (LLMs) have emerged as strong contenders in machine translation.Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study,…

Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametric knowledge may cause them to overlook contextual cues,…

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…