PRISM: Efficient Long-Range Reasoning With Short-Context LLMs

• URL: http://arxiv.org/abs/2412.18914v3
• Date: Sun, 24 Aug 2025 22:09:57 GMT
• Title: PRISM: Efficient Long-Range Reasoning With Short-Context LLMs
• Authors: Dulhan Jayalath, James Bradley Wendt, Nicholas Monath, Sandeep Tata, Beliz Gunel,
• Abstract summary: PRISM is a highly token-efficient in-context method based on structured schemas that outperforms baselines on diverse tasks with 4x shorter contexts.<n> PRISM scales down to tiny contexts without increasing costs or sacrificing quality, and generalizes to new tasks with minimal effort.
• Score: 9.765301809261159
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented generation (RAG) entails complex task-specific designs. Though in-context approaches overcome many of these issues, methods with short-context LLMs are inefficient, trading context for processing more tokens. We introduce PRISM, a highly token-efficient in-context method based on structured schemas that outperforms baselines on diverse tasks with 4x shorter contexts. This approach produces concise outputs and efficiently leverages key-value (KV) caches to reduce costs by up to 54%. PRISM scales down to tiny contexts without increasing costs or sacrificing quality, and generalizes to new tasks with minimal effort by generating schemas from task descriptions.

Related papers

• Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning [4.338036373287262]
  ARTER presents a structured pipeline that achieves high performance without deep fine-tuning.<n>It strategically combines candidate generation, context-based scoring, adaptive routing, and selective reasoning.<n>On standard benchmarks, ARTER outperforms ReFinED by up to +4.47%, with an average gain of +2.53% on 5 out of 6 datasets.
  arXiv  Detail & Related papers  (2025-10-23T00:50:14Z)
• Efficient Graph Understanding with LLMs via Structured Context Injection [8.393355845456659]
  We present a framework for structured context injection, where task-specific information is systematically embedded in the input to guide LLMs in solving a wide range of graph problems.<n>Our method does not require fine-tuning of LLMs, making it cost-efficient and lightweight.<n>We evaluate the approach on multiple graph tasks using both lightweight and large models, highlighting the trade-offs between accuracy and computational cost.
  arXiv  Detail & Related papers  (2025-08-31T08:07:56Z)
• Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models [11.012474205717178]
  Large Language Models (LLMs) are increasingly deployed across edge and cloud platforms for real-time question-answering and retrieval-augmented generation.<n>This paper introduces a novel semantic caching approach for storing and reusing contextual summaries.<n>Our method reduces redundant computations by up to 50-60% while maintaining answer accuracy comparable to full document processing.
  arXiv  Detail & Related papers  (2025-05-16T14:04:31Z)
• Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation [15.975325252309554]
  We introduce a novel post-training synthetic data generation strategy designed to efficiently extend the context window of Large Language Models. Our approach scalably extends to arbitrarily long context lengths, unconstrained by the length of available real-world data. We demonstrate that our model, with a context length of up to 1M tokens, performs well on the RULER benchmark and InfiniteBench.
  arXiv  Detail & Related papers  (2025-04-17T04:46:57Z)
• Cost-Optimal Grouped-Query Attention for Long-Context LLMs [64.90662568387683]
  Building effective Transformer-based large language models (LLMs) has recently become a research focus. We compare models with different parameter sizes, context lengths, and attention head configurations in terms of model performance, computational cost, and memory cost. Our studies show that, when processing sufficiently long sequences, a larger model with fewer attention heads can achieve a lower loss while incurring lower computational and memory costs.
  arXiv  Detail & Related papers  (2025-03-12T17:50:42Z)
• PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention [73.26995918610669]
  Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts.<n>We introduce PowerAttention, a novel sparse attention design that facilitates effective and complete context extension.<n>Experiments demonstrate that PowerAttention outperforms existing static sparse attention methods by $5sim 40%$.
  arXiv  Detail & Related papers  (2025-03-05T15:24:11Z)
• WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale [86.25450054683172]
  WildLong extracts meta-information from real user queries to produce scalable data. It supports multi-document reasoning, such as cross-document comparison and aggregation. It surpasses existing open-source long-context-optimized models across benchmarks.
  arXiv  Detail & Related papers  (2025-02-23T18:59:09Z)
• Does RAG Really Perform Bad For Long-Context Processing? [15.889864680212147]
  RetroLM is a novel framework for long-context processing.<n>Unlike traditional methods, RetroLM employs KV-level retrieval augmentation.<n>Building on this framework, we develop a specialized retriever for precise retrieval of critical pages.
  arXiv  Detail & Related papers  (2025-02-17T05:02:25Z)
• An Effective Framework to Help Large Language Models Handle Numeric-involved Long-context Tasks [0.0]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long texts.<n>Their performance significantly degrades when it comes to numerical calculations in the long-context.<n>We propose a workflow which decomposes a numeric-involved long-context task into 4 low-level subtasks.<n>The results in 2 numeric-involved long-context benchmarks demonstrate our workflow can not only improve accuracy, but also significantly reduce the cost of API calls.
  arXiv  Detail & Related papers  (2024-11-15T12:39:02Z)
• KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches [52.02764371205856]
  Long context capability is a crucial competency for large language models (LLMs) This work provides a taxonomy of current methods and evaluating 10+ state-of-the-art approaches across seven categories of long context tasks.
  arXiv  Detail & Related papers  (2024-07-01T17:59:47Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens. Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Long Context Alignment with Short Instructions and Synthesized Positions [56.1267385315404]
  This paper introduces Step-Skipping Alignment (SkipAlign) It is a new technique designed to enhance the long-context capabilities of Large Language Models (LLMs) With a careful selection of the base model and alignment datasets, SkipAlign with only 6B parameters achieves it's best performance and comparable with strong baselines like GPT-3.5-Turbo-16K on LongBench.
  arXiv  Detail & Related papers  (2024-05-07T01:56:22Z)
• LLoCO: Learning Long Contexts Offline [63.3458260335454]
  We propose LLoCO, a novel approach to processing long contexts. LLoCO learns contexts offline through context compression and in-domain parameter-efficient finetuning with LoRA. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens.
  arXiv  Detail & Related papers  (2024-04-11T17:57:22Z)
• LooGLE: Can Long-Context Language Models Understand Long Contexts? [46.143956498529796]
  LooGLE is a benchmark for large language models' long context understanding. It features relatively new documents post-2022, with over 24,000 tokens per document and 6,000 newly generated questions spanning diverse domains. The evaluation of eight state-of-the-art LLMs on LooGLE revealed key findings.
  arXiv  Detail & Related papers  (2023-11-08T01:45:37Z)
• OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
  We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs. Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
  arXiv  Detail & Related papers  (2023-05-24T10:08:04Z)
• Instance-wise Prompt Tuning for Pretrained Language Models [72.74916121511662]
  Instance-wise Prompt Tuning (IPT) is the first prompt learning paradigm that injects knowledge from the input data instances to the prompts. IPT significantly outperforms task-based prompt learning methods, and achieves comparable performance to conventional finetuning with only 0.5% - 1.5% of tuned parameters.
  arXiv  Detail & Related papers  (2022-06-04T10:08:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.