Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
- URL: http://arxiv.org/abs/2410.10074v1
- Date: Mon, 14 Oct 2024 01:34:16 GMT
- Title: Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
- Authors: Chengsong Huang, Langlin Huang, Jiaxin Huang,
- Abstract summary: In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs)
We propose Logit Arithmetic Reweighting Approach (LARA), a novel framework that enhances ICL by using logit-based ensembling of multiple demonstrations.
- Score: 19.16587730306472
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs), allowing them to adapt to new tasks by leveraging task-specific examples without updating model parameters. However, ICL faces challenges with increasing numbers of examples due to performance degradation and quadratic computational costs. In this paper, we propose Logit Arithmetic Reweighting Approach (LARA), a novel framework that enhances ICL by using logit-based ensembling of multiple demonstrations. Our approach divides long input demonstrations into parallelizable shorter inputs to significantly reduce memory requirements, and then effectively aggregate the information by reweighting logits of each group via a non-gradient optimization approach. We further introduce Binary LARA (B-LARA), a variant that constrains weights to binary values to simplify the search space and reduces memory usage by filtering out less informative demonstration groups. Experiments on BBH and MMLU demonstrate that LARA and B-LARA outperform all baseline methods in both accuracy and memory efficiency. We also conduct extensive analysis to show that LARA generalizes well to scenarios of varying numbers of examples from limited to many-shot demonstrations.
Related papers
- Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities.
In-Context Learning (ICL) and.
Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting.
LLMs to downstream tasks.
We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
arXiv Detail & Related papers (2024-09-30T10:48:20Z) - Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization [0.6445087473595953]
Large language models (LLMs) demonstrate outstanding performance in various tasks in machine learning.
deploying LLM inference poses challenges due to the high compute and memory requirements.
We present Tender, an algorithm-hardware co-design solution that enables efficient deployment of LLM inference at low precision.
arXiv Detail & Related papers (2024-06-16T09:51:55Z) - DeTriever: Decoder-representation-based Retriever for Improving NL2SQL In-Context Learning [19.93800175353809]
DeTriever is a novel demonstration retrieval framework that learns a weighted combination of hidden states.
Our method significantly outperforms the state-of-the-art baselines on one-shot NL2 tasks.
arXiv Detail & Related papers (2024-06-12T06:33:54Z) - Implicit In-context Learning [37.0562059811099]
In-context Learning (ICL) empowers large language models to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries.
We introduce Implicit In-context Learning (I2CL), an innovative paradigm that addresses the challenges associated with traditional ICL by absorbing demonstration examples within the activation space.
I2CL achieves few-shot performance with zero-shot cost and exhibits robustness against the variation of demonstration examples.
arXiv Detail & Related papers (2024-05-23T14:57:52Z) - 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) - Learning to Reduce: Optimal Representations of Structured Data in
Prompting Large Language Models [42.16047343029512]
Large Language Models (LLMs) have been widely used as general-purpose AI agents.
We propose a framework, Learning to Reduce, that fine-tunes a language model to generate a reduced version of an input context.
We show that our model achieves comparable accuracies in selecting the relevant evidence from an input context.
arXiv Detail & Related papers (2024-02-22T00:41:23Z) - Which Examples to Annotate for In-Context Learning? Towards Effective
and Efficient Selection [35.924633625147365]
Large Language Models (LLMs) can adapt to new tasks via in-context learning (ICL)
In this work, we investigate an active learning approach for ICL, where there is a limited budget for annotating examples.
We propose a model-adaptive optimization-free algorithm, termed AdaICL, which identifies examples that the model is uncertain about.
arXiv Detail & Related papers (2023-10-30T22:03:55Z) - 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) - Large Language Models Are Latent Variable Models: Explaining and Finding
Good Demonstrations for In-Context Learning [104.58874584354787]
In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning.
This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models.
arXiv Detail & Related papers (2023-01-27T18:59:01Z) - Improving Meta-learning for Low-resource Text Classification and
Generation via Memory Imitation [87.98063273826702]
We propose a memory imitation meta-learning (MemIML) method that enhances the model's reliance on support sets for task adaptation.
A theoretical analysis is provided to prove the effectiveness of our method.
arXiv Detail & Related papers (2022-03-22T12:41:55Z) - A Lagrangian Duality Approach to Active Learning [119.36233726867992]
We consider the batch active learning problem, where only a subset of the training data is labeled.
We formulate the learning problem using constrained optimization, where each constraint bounds the performance of the model on labeled samples.
We show, via numerical experiments, that our proposed approach performs similarly to or better than state-of-the-art active learning methods.
arXiv Detail & Related papers (2022-02-08T19:18:49Z)
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.