pith. sign in

arxiv: 2312.09571 · v1 · pith:AZX2GBL7new · submitted 2023-12-15 · 💻 cs.CL · cs.IT· math.IT

Extending Context Window of Large Language Models via Semantic Compression

classification 💻 cs.CL cs.ITmath.IT
keywords semanticcompressionllmsmethodcomputationalcontextgenerationinformation
0
0 comments X
read the original abstract

Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. This constraint restricts their applicability in scenarios involving long texts. We propose a novel semantic compression method that enables generalization to texts that are 6-8 times longer, without incurring significant computational costs or requiring fine-tuning. Our proposed framework draws inspiration from source coding in information theory and employs a pre-trained model to reduce the semantic redundancy of long inputs before passing them to the LLMs for downstream tasks. Experimental results demonstrate that our method effectively extends the context window of LLMs across a range of tasks including question answering, summarization, few-shot learning, and information retrieval. Furthermore, the proposed semantic compression method exhibits consistent fluency in text generation while reducing the associated computational overhead.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Coupling Language Models with Physics-based Simulation for Synthesis of Inorganic Materials

    cs.AI 2026-05 unverdicted novelty 5.0

    A hybrid LLM-plus-physics-simulation framework generates synthesis routes for niobium oxides and finds that LLM implicit priors produce more viable plans than classical path-planning algorithms in computational tests.

  2. DisCEdge: Distributed Context Management for Large Language Models at the Edge

    cs.DC 2025-11 unverdicted novelty 5.0

    DisCEdge manages LLM context in tokenized form replicated on edge nodes, delivering up to 14.46% faster median responses, 15% lower sync overhead, and 90% smaller client requests versus baselines while ensuring consistency.

  3. A Survey on Efficient Inference for Large Language Models

    cs.CL 2024-04 accept novelty 3.0

    The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.