Iterative Forward Tuning Boosts In-Context Learning in Language Models
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.
Code (1)
Tasks
Decision MakingIn-Context LearningMultiple-choicePrompt EngineeringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Integrating Multimodal Information in Large Pretrained Transformers
Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific d…
Multimodal Sentiment AnalysisQuestion AnsweringSentiment AnalysisLeveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards
Recent studies show that large language models (LLMs) struggle with technical standards in telecommunications. We propose a fine-tuned retrieval-augmented generation (RAG) system based on the Phi-2 small language model (…
ChunkingComputational EfficiencyLanguage ModellingQuestion Answering+5Symbol tuning improves in-context learning in language models
We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrary symbols (e.g., "foo/bar"). Symbol tuni…
In-Context LearningAgent Q: Advanced Reasoning and Learning for Autonomous AI Agents
Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a diff…
Decision MakingOptimization through In-Context Learning and Iterative LLM Prompting for Nuclear Engineering Design Problems
The optimization of nuclear engineering designs, such as nuclear fuel assembly configurations, involves managing competing objectives like reactivity control and power distribution. This study explores the use of Optimiz…
In-Context LearningMetaheuristic Optimization