Focused Large Language Models are Stable Many-Shot Learners

• URL: http://arxiv.org/abs/2408.13987v1
• Date: Mon, 26 Aug 2024 02:53:24 GMT
• Title: Focused Large Language Models are Stable Many-Shot Learners
• Authors: Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li,
• Abstract summary: In-Context Learning (ICL) enables large language models (LLMs) to achieve rapid task adaptation by learning from demonstrations. We propose a training-free method FocusICL, which conducts triviality filtering to avoid attention being diverted by unimportant contents. We show that FocusICL achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations.
• Score: 18.783939647966776
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In-Context Learning (ICL) enables large language models (LLMs) to achieve rapid task adaptation by learning from demonstrations. With the increase in available context length of LLMs, recent experiments have shown that the performance of ICL does not necessarily scale well in many-shot (demonstration) settings. We theoretically and experimentally confirm that the reason lies in more demonstrations dispersing the model attention from the query, hindering its understanding of key content. Inspired by how humans learn from examples, we propose a training-free method FocusICL, which conducts triviality filtering to avoid attention being diverted by unimportant contents at token-level and operates hierarchical attention to further ensure sufficient attention towards current query at demonstration-level. We also design an efficient hyperparameter searching strategy for FocusICL based on model perplexity of demonstrations. Comprehensive experiments validate that FocusICL achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations.

Related papers

• Evaluating Linguistic Capabilities of Multimodal LLMs in the Lens of Few-Shot Learning [15.919493497867567]
  This study aims to evaluate the performance of Multimodal Large Language Models (MLLMs) on the VALSE benchmark. We conducted a comprehensive assessment of state-of-the-art MLLMs, varying in model size and pretraining datasets.
  arXiv  Detail & Related papers  (2024-07-17T11:26:47Z)
• Towards Multimodal In-Context Learning for Vision & Language Models [21.69457980865084]
  State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality. We propose a simple yet surprisingly effective multi-turn curriculum-based learning methodology with effective data mixes.
  arXiv  Detail & Related papers  (2024-03-19T13:53:37Z)
• In-Context Learning Demonstration Selection via Influence Analysis [11.504012974208466]
  Large Language Models (LLMs) have showcased their In-Context Learning (ICL) capabilities. Despite its advantages, the effectiveness of ICL heavily depends on the choice of demonstrations. We propose a demonstration selection method named InfICL, which utilizes influence functions to analyze impacts of training samples.
  arXiv  Detail & Related papers  (2024-02-19T00:39:31Z)
• Comparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selection [22.29452683679149]
  In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. This study explores the ICL mechanisms from a novel perspective, providing a deeper insight into the demonstration selection strategy for ICL.
  arXiv  Detail & Related papers  (2023-12-12T18:05:46Z)
• Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks [54.153914606302486]
  In-context learning (ICL) ability has emerged with the increasing scale of large language models (LLMs) We propose a new paradigm called Hint-enhanced In-Context Learning (HICL) to explore the power of ICL in open-domain question answering.
  arXiv  Detail & Related papers  (2023-11-03T14:39:20Z)
• Improving Input-label Mapping with Demonstration Replay for In-context Learning [67.57288926736923]
  In-context learning (ICL) is an emerging capability of large autoregressive language models. We propose a novel ICL method called Sliding Causal Attention (RdSca) We show that our method significantly improves the input-label mapping in ICL demonstrations.
  arXiv  Detail & Related papers  (2023-10-30T14:29:41Z)
• 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)
• Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning [67.25698169440818]
  Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL) We train the same LLMs with the same demonstration examples via ICL and supervised learning (SL), respectively, and investigate their performance under label perturbations. First, we find that gold labels have significant impacts on the downstream in-context performance, especially for large language models. Second, when comparing with SL, we show empirically that ICL is less sensitive to label perturbations than SL, and ICL gradually attains comparable performance to SL as the model size increases.
  arXiv  Detail & Related papers  (2023-07-28T09:03:19Z)
• Scaling In-Context Demonstrations with Structured Attention [75.41845145597875]
  We propose a better architectural design for in-context learning. Structured Attention for In-Context Learning replaces the full-attention by a structured attention mechanism. We show that SAICL achieves comparable or better performance than full attention while obtaining up to 3.4x inference speed-up.
  arXiv  Detail & Related papers  (2023-07-05T23:26:01Z)
• 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)

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.