Related papers: Enhancing Long-Term Memory using Hierarchical Aggr…
In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3)…
Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structured retrieval and reasoning. However, existing graph-based…
Large language models often expose their brittleness in reasoning tasks, especially while executing long chains of reasoning over context. We propose MemReasoner, a new and simple memory-augmented LLM architecture, in which the memory…
With the widespread adoption of large language models (LLMs) in numerous applications, the challenge of factuality and the propensity for hallucinations has emerged as a significant concern. To address this issue, particularly in…
In multi-turn dialogue generation, responses are not only related to the topic and background of the context but also related to words and phrases in the sentences of the context. However, currently widely used hierarchical dialog models…
Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of…
Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a…
Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmented Generation…
Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation…
Retrieval-Augmented Generation (RAG) has become an essential approach for extending the reasoning and knowledge capacity of large language models (LLMs). While prior research has primarily focused on retrieval quality and prompting…
As an effective method to boost the performance of Large Language Models (LLMs) on the question answering (QA) task, Retrieval-Augmented Generation (RAG), which queries highly relevant information from external complex documents, has…
In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to…
Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has…
This paper presents Loops On Retrieval Augmented Generation (LoRAG), a new framework designed to enhance the quality of retrieval-augmented text generation through the incorporation of an iterative loop mechanism. The architecture…
Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory grow rapidly with prompt length. Flat token-stream processing…
Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking…
Most existing audio-text retrieval (ATR) methods focus on constructing contrastive pairs between whole audio clips and complete caption sentences, while ignoring fine-grained cross-modal relationships, e.g., short segments and phrases or…
The computational complexity of the self-attention mechanism in Transformer models significantly limits their ability to generalize over long temporal durations. Memory-augmentation, or the explicit storing of past information in external…
This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is…
Recent advancements in Large Language Models (LLMs) have yielded remarkable success across diverse fields. However, handling long contexts remains a significant challenge for LLMs due to the quadratic time and space complexity of attention…