Related papers: HoReN: Normalized Hopfield Retrieval for Large-Sca…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Modern large language models often encode sensitive, harmful, or copyrighted knowledge, raising the need for post-hoc unlearning-the ability to remove specific domains of knowledge from a model without full retraining. A major bottleneck in…

We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on…

Large Language Models (LLMs) often exhibit inconsistent behavior when answering paraphrased questions, suggesting a reliance on surface-level patterns rather than true semantic understanding. To address this limitation, we introduce RoParQ,…

The Hopfield model is a pioneering neural network model with associative memory retrieval. The analytical solution of the model in mean field limit revealed that memories can be retrieved without any error up to a finite storage capacity of…

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdated information within these models can undermine their…

The present paper provides a generalized model of network, namely, Hybrid Layered Network (HLN). We proved that the sets of all homogeneous, heterogeneous and multi-layered networks are subsets of the set of all HLNs depicting the model's…

Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the…

Handwritten text recognition is an open problem of great interest in the area of automatic document image analysis. The transcription of handwritten content present in digitized documents is significant in analyzing historical archives or…

Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embedding Fusion (HEF), a…

Knowledge editing aims to update outdated information in Large Language Models (LLMs). A representative line of study is locate-then-edit methods, which typically employ causal tracing to identify the modules responsible for recalling…

Modern distributed systems produce massive, heterogeneous logs essential for reliability, security, and anomaly detection. Converting these free-form messages into structured templates (log parsing) is challenging due to evolving formats…

Consistency of a model -- that is, the invariance of its behavior under meaning-preserving alternations in its input -- is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained…

Despite the great success of large language models (LLMs), efficiently controlling the length of the output sequence still remains a challenge. In this paper, we propose Hansel, an efficient framework for length control in LLMs without…

Why do even the most powerful 7B-parameter embedding models struggle with simple retrieval tasks that the decades old BM25 handles with ease? Recent theory suggests that this happens because of a dimensionality bottleneck. This occurs when…

This paper presents a waveform modeling and generation method using hierarchical recurrent neural networks (HRNN) for speech bandwidth extension (BWE). Different from conventional BWE methods which predict spectral parameters for…

Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…

We introduce HAMLET, a holistic and automated framework for evaluating the long-context comprehension of large language models (LLMs). HAMLET structures source texts into a three-level key-fact hierarchy at root-, branch-, and leaf-levels,…

Addressing the issues of hallucinations and outdated knowledge in large language models is critical for their reliable application. Model Editing presents a promising avenue for mitigating these challenges in a cost-effective manner.…