Parse Trees Guided LLM Prompt Compression

• URL: http://arxiv.org/abs/2409.15395v1
• Date: Mon, 23 Sep 2024 06:21:40 GMT
• Title: Parse Trees Guided LLM Prompt Compression
• Authors: Wenhao Mao, Chengbin Hou, Tianyu Zhang, Xinyu Lin, Ke Tang, Hairong Lv,
• Abstract summary: We propose a novel selective compression method called PartPrompt. It first obtains a parse tree for each sentence based on linguistic rules, and calculates local information entropy for each node in a parse tree. The experiments show that PartPrompt receives the state-of-the-art performance across various datasets.
• Score: 20.61121589698341
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Offering rich contexts to Large Language Models (LLMs) has shown to boost the performance in various tasks, but the resulting longer prompt would increase the computational cost and might exceed the input limit of LLMs. Recently, some prompt compression methods have been suggested to shorten the length of prompts by using language models to generate shorter prompts or by developing computational models to select important parts of original prompt. The generative compression methods would suffer from issues like hallucination, while the selective compression methods have not involved linguistic rules and overlook the global structure of prompt. To this end, we propose a novel selective compression method called PartPrompt. It first obtains a parse tree for each sentence based on linguistic rules, and calculates local information entropy for each node in a parse tree. These local parse trees are then organized into a global tree according to the hierarchical structure such as the dependency of sentences, paragraphs, and sections. After that, the root-ward propagation and leaf-ward propagation are proposed to adjust node values over the global tree. Finally, a recursive algorithm is developed to prune the global tree based on the adjusted node values. The experiments show that PartPrompt receives the state-of-the-art performance across various datasets, metrics, compression ratios, and target LLMs for inference. The in-depth ablation studies confirm the effectiveness of designs in PartPrompt, and other additional experiments also demonstrate its superiority in terms of the coherence of compressed prompts and in the extreme long prompt scenario.

Related papers

• LiteSearch: Efficacious Tree Search for LLM [70.29796112457662]
  This study introduces a novel guided tree search algorithm with dynamic node selection and node-level exploration budget. Experiments conducted on the GSM8K and TabMWP datasets demonstrate that our approach enjoys significantly lower computational costs compared to baseline methods.
  arXiv  Detail & Related papers  (2024-06-29T05:14:04Z)
• Nearest Neighbor Speculative Decoding for LLM Generation and Attribution [87.3259169631789]
  Nearest Speculative Decoding (NEST) is capable of incorporating real-world text spans of arbitrary length into the LM generations and providing attribution to their sources. NEST significantly enhances the generation quality and attribution rate of the base LM across a variety of knowledge-intensive tasks. In addition, NEST substantially improves the generation speed, achieving a 1.8x speedup in inference time when applied to Llama-2-Chat 70B.
  arXiv  Detail & Related papers  (2024-05-29T17:55:03Z)
• Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement [11.91629418177851]
  Speculative decoding is an inference-accel method for large language models. Recent works have advanced this method by establishing a draft-token tree. We present Recursive Speculative Decoding (RSD), a novel tree-based method that samples draft tokens without replacement.
  arXiv  Detail & Related papers  (2024-02-21T22:57:49Z)
• Tree Prompting: Efficient Task Adaptation without Fine-Tuning [112.71020326388029]
  Tree Prompting builds a decision tree of prompts, linking multiple LM calls together to solve a task. Experiments on classification datasets show that Tree Prompting improves accuracy over competing methods and is competitive with fine-tuning.
  arXiv  Detail & Related papers  (2023-10-21T15:18:22Z)
• TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding [17.9785504685384]
  We propose a new prompt construction paradigm with explicit explainable ability, named TreePrompt. Specifically, we first deconstruct a complex sentence into a tree, that is consistent with human reasoning. Thanks to this step-by-step prompt construction process, each intermediate prompt (i.e., tree node) permits us to understand the reasoning process.
  arXiv  Detail & Related papers  (2023-05-19T07:52:22Z)
• Hypotheses Tree Building for One-Shot Temporal Sentence Localization [53.82714065005299]
  One-shot temporal sentence localization (one-shot TSL) learns to retrieve the query information among the entire video with only one annotated frame. We propose an effective and novel tree-structure baseline for one-shot TSL, called Multiple Hypotheses Segment Tree (MHST) MHST captures the query-aware discriminative frame-wise information under the insufficient annotations.
  arXiv  Detail & Related papers  (2023-01-05T01:50:43Z)
• Explaining Patterns in Data with Language Models via Interpretable Autoprompting [143.4162028260874]
  We introduce interpretable autoprompting (iPrompt), an algorithm that generates a natural-language string explaining the data. iPrompt can yield meaningful insights by accurately finding groundtruth dataset descriptions. Experiments with an fMRI dataset show the potential for iPrompt to aid in scientific discovery.
  arXiv  Detail & Related papers  (2022-10-04T18:32:14Z)
• TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding [56.794981024301094]
  We propose a compositional data augmentation approach for natural language understanding called TreeMix. Specifically, TreeMix leverages constituency parsing tree to decompose sentences into constituent sub-structures and the Mixup data augmentation technique to recombine them to generate new sentences. Compared with previous approaches, TreeMix introduces greater diversity to the samples generated and encourages models to learn compositionality of NLP data.
  arXiv  Detail & Related papers  (2022-05-12T15:25:12Z)
• RST Parsing from Scratch [14.548146390081778]
  We introduce a novel end-to-end formulation of document-level discourse parsing in the Rhetorical Structure Theory (RST) framework. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high-scoring trees.
  arXiv  Detail & Related papers  (2021-05-23T06:19:38Z)
• Unsupervised Learning of Discourse Structures using a Tree Autoencoder [8.005512864082126]
  We propose a new strategy to generate tree structures in a task-agnostic, unsupervised fashion by extending a latent tree induction framework with an auto-encoding objective. The proposed approach can be applied to any tree objective, such as syntactic parsing, discourse parsing and others. In this paper we are inferring general tree structures of natural text in multiple domains, showing promising results on a diverse set of tasks.
  arXiv  Detail & Related papers  (2020-12-17T08:40:34Z)

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.