paper-with-me

홈 › Papers

Iterative Forward Tuning Boosts In-Context Learning in Language Models

2023-05-22 · Jiaxi Yang, Binyuan Hui, Min Yang, Bailin Wang, Bowen Li, Binhua Li, Fei Huang, Yongbin Li

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.

📄 PDF Abstract BibTeX arXiv:2305.13016

Code (1)

yangjiaxi/deepthinking 공식 구현

Tasks

Decision MakingIn-Context LearningMultiple-choicePrompt Engineering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Test 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Integrating Multimodal Information in Large Pretrained Transformers

2019-08-15 · ACL 2020 6 · Wasifur Rahman, Md. Kamrul Hasan, Sangwu Lee, Amir Zadeh 외

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 Analysis

Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards

2024-08-21 · Omar Erak, Nouf Alabbasi, Omar Alhussein, Ismail Lotfi 외

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+5

Symbol tuning improves in-context learning in language models

2023-05-15 · Jerry Wei, Le Hou, Andrew Lampinen, Xiangning Chen 외

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 Learning

Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

2024-08-13 · Pranav Putta, Edmund Mills, Naman Garg, Sumeet Motwani 외

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 Making

Optimization through In-Context Learning and Iterative LLM Prompting for Nuclear Engineering Design Problems

2025-03-25 · M. Rizki Oktavian, Anirudh Tunga, Amandeep Bakshi, Michael J. Mueterthies 외

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