Iterative Forward Tuning Boosts In-Context Learning in Language Models
- URL: http://arxiv.org/abs/2305.13016v3
- Date: Tue, 4 Jun 2024 05:49:01 GMT
- Title: Iterative Forward Tuning Boosts In-Context Learning in Language Models
- Authors: Jiaxi Yang, Binyuan Hui, Min Yang, Bailin Wang, Bowen Li, Binhua Li, Fei Huang, Yongbin Li,
- Abstract summary: 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.
- Score: 88.25013390669845
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite the advancements in in-context learning (ICL) for large language models (LLMs), current research centers on specific prompt engineering, such as demonstration selection, with the expectation that a single iteration of demonstrations processing can generalize effectively to a given test sample. However, this perspective overlooks the potential benefits derived from multiple iterations involving demonstrations, a practice aligning more closely with the iterative decision-making process exhibited by humans, who often learn through analogy. In this study, we introduce a novel two-stage framework to boost ICL in 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. This mechanism operates by manipulating the Key-Value matrices without training, fostering enhanced understanding capabilities in LLMs by thinking demonstrations multiple times. We evaluated Deep-Thinking across a range of benchmarks and LLMs, showing its superior performance over vanilla ICL methods and its effectiveness in challenging tasks where demonstration selection is infeasible.
Related papers
- Investigating the Zone of Proximal Development of Language Models for In-Context Learning [59.91708683601029]
We introduce a learning analytics framework to analyze the in-context learning (ICL) behavior of large language models (LLMs)
We adapt the Zone of Proximal Development (ZPD) theory to ICL, measuring the ZPD of LLMs based on model performance on individual examples.
Our findings reveal a series of intricate and multifaceted behaviors of ICL, providing new insights into understanding and leveraging this technique.
arXiv Detail & Related papers (2025-02-10T19:36:21Z) - Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.
Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.
We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
arXiv Detail & Related papers (2025-02-04T17:26:58Z) - Focused Large Language Models are Stable Many-Shot Learners [18.783939647966776]
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.
arXiv Detail & Related papers (2024-08-26T02:53:24Z) - Large Language Models Know What Makes Exemplary Contexts [42.90814615222177]
In-context learning (ICL) has proven to be a significant capability with the advancement of Large Language models (LLMs)
This paper presents a unified framework for LLMs that allows them to self-select influential in-context examples to compose their contexts.
arXiv Detail & Related papers (2024-08-14T12:32:41Z) - ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models [73.34709921061928]
We propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs)
We optimize a learnable latent variable based on an energy function, enhancing the strength of referring regions in the attention map.
Our method offers a promising direction for integrating referring abilities into MLLMs, and supports referring with box, mask, scribble and point.
arXiv Detail & Related papers (2024-07-31T11:40:29Z) - Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning [43.356895599336504]
We analyze the working mechanisms of the learning-based demonstration selection methods.
We empirically identify two important factors related to similarity measurement.
We introduce two effective yet simplified exemplar selection methods catering to task-agnostic and task-specific demands.
arXiv Detail & Related papers (2024-06-14T03:34:02Z) - 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) - Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning [9.660673938961416]
Demonstration ordering is an important strategy for in-context learning (ICL)
We propose a simple but effective demonstration ordering method for ICL, named the few-shot In-Context Curriculum Learning (ICCL)
arXiv Detail & Related papers (2024-02-16T14:55:33Z) - 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)
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.