相关论文: Retaining Key Information under High Compression R…

We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) language model (LM) for guiding a black-box large (i.e., >10B) LM in reasoning tasks. Specifically, the lightweight LM first generates a rationale for…

Large Reasoning Models (LRMs) perform strongly in complex reasoning tasks via Chain-of-Thought (CoT) prompting, but often suffer from verbose outputs, increasing computational overhead. Existing fine-tuning-based compression methods either…

The advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on scaling model parameters. However, as hardware limits constrain further model growth, the primary computational bottleneck has shifted…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval-generation optimization. In this work, we propose CLaRa (Continuous Latent…

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

Knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and contextual awareness. Unfortunately, current methods often…

Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks…

The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate…

This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term,…

The relentless expansion of scientific literature presents significant challenges for navigation and knowledge discovery. Within Research Information Retrieval, established tasks such as text summarization and classification remain crucial…

The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…

Prompt compression condenses contexts while maintaining their informativeness for different usage scenarios. It not only shortens the inference time and reduces computational costs during the usage of large language models, but also lowers…

Data compression continues to evolve, with traditional information theory methods being widely used for compressing text, images, and videos. Recently, there has been growing interest in leveraging Generative AI for predictive compression…

Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens…

The development of large language models (LLMs) has achieved superior performance in a range of downstream tasks, including LLM-based retrieval-augmented generation (RAG). The quality of generated content heavily relies on the usefulness of…

Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and natural-language reasoning abilities. Despite recent progress, current LLM-based…

Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these…

Although applications involving long-context inputs are crucial for the effective utilization of large language models (LLMs), they also result in increased computational costs and reduced performance. To address this challenge, we propose…

Knowledge tracing (KT), wherein students' problem-solving histories are used to estimate their current levels of knowledge, has attracted significant interest from researchers. However, most existing KT models were developed with an…

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…