Unifying Demonstration Selection and Compression for In-Context Learning

• URL: http://arxiv.org/abs/2405.17062v2
• Date: Sat, 15 Jun 2024 21:16:57 GMT
• Title: Unifying Demonstration Selection and Compression for In-Context Learning
• Authors: Jun Gao, Ziqiang Cao, Wenjie Li,
• Abstract summary: We propose an ICL framework UniICL, which Unifies demonstration selection and compression, and final response generation via a single frozen LLM. UniICL is a parameter-efficient framework that only contains 17M trainable parameters originating from the projection layer.
• Score: 14.545490629324295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In-context learning (ICL) facilitates large language models (LLMs) exhibiting spectacular emergent capabilities in various scenarios. Unfortunately, introducing demonstrations easily makes the prompt length explode, bringing a significant burden to hardware. In addition, random demonstrations usually achieve limited improvements in ICL, necessitating demonstration selection among accessible candidates. Previous studies introduce extra modules to perform demonstration compression or selection independently. In this paper, we propose an ICL framework UniICL, which Unifies demonstration selection and compression, and final response generation via a single frozen LLM. Specifically, UniICL first projects actual demonstrations and inference text inputs into short virtual tokens, respectively. Then, virtual tokens are applied to select suitable demonstrations by measuring semantic similarity within latent space among candidate demonstrations and inference input. Finally, inference text inputs together with selected virtual demonstrations are fed into the same frozen LLM for response generation. Notably, UniICL is a parameter-efficient framework that only contains 17M trainable parameters originating from the projection layer. We conduct experiments and analysis over in- and out-domain datasets of both generative and understanding tasks, encompassing ICL scenarios with plentiful and limited demonstration candidates. Results show that UniICL effectively unifies $12 \times$ compression, demonstration selection, and response generation, efficiently scaling up the baseline from 4-shot to 64-shot ICL in IMDb with 24 GB CUDA allocation

Related papers

• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)
• Efficient Multi-modal Long Context Learning for Training-free Adaptation [96.21248144937627]
  This paper introduces Efficient Multi-Modal Long Context Learning (EMLoC)<n>It embeds demonstration examples directly into the model input.<n>It condenses long-context multimodal inputs into compact, task-specific memory representations.
  arXiv  Detail & Related papers  (2025-05-26T10:49:44Z)
• MateICL: Mitigating Attention Dispersion in Large-Scale In-Context Learning [0.0]
  We introduce Mitigating Attention Dispersion in large-scale ICL (MateICL)<n>We show that MateICL can effectively leverage larger contexts to improve ICL performance.<n>Despite advances in inference strategies, our results demonstrate that MateICL remains beneficial in computationally resource-constrained settings.
  arXiv  Detail & Related papers  (2025-05-02T08:45:45Z)
• PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection [56.916656013563355]
  In-context learning (ICL) enables Large Language Models to perform tasks using few demonstrations. We propose PICLe, a framework for in-context learning with noisy, pseudo-annotated demonstrations. We evaluate PICLe on five biomedical NED datasets and show that, with zero human annotation, PICLe outperforms ICL in low-resource settings.
  arXiv  Detail & Related papers  (2024-12-16T16:09:35Z)
• BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression [91.23933111083389]
  Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge.<n>This paper presents BRIEF, a lightweight approach that performs query-aware multi-hop reasoning.<n>Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries.
  arXiv  Detail & Related papers  (2024-10-20T04:24:16Z)
• Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost [4.5650448738679605]
  Large language models (LLMs) can solve challenging question-answering tasks.<n> prompt engineering techniques, such as chain-of-thought (CoT), have gained attention for enhancing the explanation and correctness of outputs.
  arXiv  Detail & Related papers  (2024-07-29T09:21:52Z)
• Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models [21.025001473355996]
  We formalize the problem of prompt compression for large language models (LLMs)<n>We present a framework to unify token-level prompt compression methods which create hard prompts for black-box models.<n>We show that there is a large gap between the performance of current prompt compression methods and the optimal strategy.
  arXiv  Detail & Related papers  (2024-07-22T09:40:13Z)
• In-Context Former: Lightning-fast Compressing Context for Large Language Model [48.831304302467004]
  In this paper, we propose a new approach to compress the long input contexts of Transformer-based large language models (LLMs) We use the cross-attention mechanism and a small number of learnable digest tokens to condense information from the contextual word embeddings. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times.
  arXiv  Detail & Related papers  (2024-06-19T15:14:55Z)
• Show, Don't Tell: Aligning Language Models with Demonstrated Feedback [54.10302745921713]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors. We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• ParaICL: Towards Robust Parallel In-Context Learning [74.38022919598443]
  Large language models (LLMs) have become the norm in natural language processing. Few-shot in-context learning (ICL) relies on the choice of few-shot demonstration examples. We propose a novel method named parallel in-context learning (ParaICL)
  arXiv  Detail & Related papers  (2024-03-31T05:56:15Z)
• Extending Context Window of Large Language Models via Semantic Compression [21.35020344956721]
  Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. We propose a novel semantic compression method that enables generalization to texts 6-8 times longer, without incurring significant computational costs or requiring fine-tuning.
  arXiv  Detail & Related papers  (2023-12-15T07:04:33Z)
• In-Context Learning with Iterative Demonstration Selection [32.62104857810135]
  Large language models (LLMs) have demonstrated strong few-shot learning ability via in-context learning (ICL) The performance of ICL has been shown to be highly sensitive to the selection of few-shot demonstrations. We propose Iterative Demonstration Selection (IDS) to leverage the merits of both dimensions.
  arXiv  Detail & Related papers  (2023-10-15T16:40:19Z)
• LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models [22.06402870816756]
  Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. This paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity. We show that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss.
  arXiv  Detail & Related papers  (2023-10-09T14:10:21Z)
• Dynamic Demonstrations Controller for In-Context Learning [51.3439660534631]
  In-Context Learning (ICL) is a new paradigm for natural language processing (NLP), where a large language model observes a small number of demonstrations and a test instance as its input. Previous studies have revealed that ICL is sensitive to the selection and the ordering of demonstrations. We propose a Dynamic Demonstrations Controller (D$2$Controller), which can improve the ICL performance by adjusting the number of demonstrations.
  arXiv  Detail & Related papers  (2023-09-30T14:04:22Z)
• Are Human-generated Demonstrations Necessary for In-context Learning? [22.783456038837794]
  Self-contemplation prompting strategy (SEC) is a paradigm free from human-crafted demonstrations. Extensive experiments in arithmetic reasoning, commonsense reasoning, multi-task language understanding, and code generation benchmarks, show that SEC significantly outperforms the zero-shot learning strategy.
  arXiv  Detail & Related papers  (2023-09-26T05:10:08Z)
• Ambiguity-Aware In-Context Learning with Large Language Models [27.20414960164616]
  In-context learning (ICL) i.e. showing LLMs task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. This study investigates how to select good demonstrations for ICL. We find that it is beneficial to not only choose semantically similar ICL demonstrations but also to choose those that help resolve the inherent label ambiguity surrounding the test example.
  arXiv  Detail & Related papers  (2023-09-14T17:48:34Z)
• Exploring Demonstration Ensembling for In-context Learning [75.35436025709049]
  In-context learning (ICL) operates by showing language models (LMs) examples of input-output pairs for a given task. The standard approach for ICL is to prompt the LMd demonstrations followed by the test input. In this work, we explore Demonstration Ensembling (DENSE) as an alternative to simple concatenation.
  arXiv  Detail & Related papers  (2023-08-17T04:45:19Z)
• In-context Autoencoder for Context Compression in a Large Language Model [70.7621953091318]
  We propose the In-context Autoencoder (ICAE) to compress a long context into short compact memory slots. ICAE is first pretrained using both autoencoding and language modeling objectives on massive text data.
  arXiv  Detail & Related papers  (2023-07-13T17:59:21Z)
• Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations [38.4166247280112]
  Self-ICL is a framework which bootstraps LMs' intrinsic capabilities to perform zero-shot ICL. Self-ICL outperforms zero-shot baselines on both average accuracy and head-to-head comparison.
  arXiv  Detail & Related papers  (2023-05-24T11:22:34Z)
• Dr.ICL: Demonstration-Retrieved In-context Learning [29.142262267850704]
  In-context learning (ICL) teaching a large language model to perform a task with few-shot demonstrations has emerged as a strong paradigm for using LLMs. Recent research suggests that retrieving semantically similar demonstrations to the input from a pool of available demonstrations results in better performance. This work expands the applicability of retrieval-based ICL approaches by demonstrating that even simple word-overlap similarity measures such as BM25 outperform randomly selected demonstrations.
  arXiv  Detail & Related papers  (2023-05-23T14:55:25Z)
• Iterative Forward Tuning Boosts In-Context Learning in Language Models [88.25013390669845]
  In this study, we introduce a novel two-stage framework to boost in-context learning in large language models (LLMs) Specifically, our framework delineates the ICL process into two distinct stages: Deep-Thinking and test stages. The Deep-Thinking stage incorporates a unique attention mechanism, i.e., iterative enhanced attention, which enables multiple rounds of information accumulation.
  arXiv  Detail & Related papers  (2023-05-22T13:18:17Z)
• ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction [56.790794611002106]
  Large language models (LLMs) have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning. We propose a simple but effective in-context learning framework called ICL-D3IE. Specifically, we extract the most difficult and distinct segments from hard training documents as hard demonstrations.
  arXiv  Detail & Related papers  (2023-03-09T06:24:50Z)

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.