From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
- URL: http://arxiv.org/abs/2406.19292v1
- Date: Thu, 27 Jun 2024 16:05:13 GMT
- Title: From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
- Authors: Zheyang Xiong, Vasilis Papageorgiou, Kangwook Lee, Dimitris Papailiopoulos,
- Abstract summary: Finetuning models for long-context processing improves their information retrieval and reasoning capabilities.
We present an analysis of the finetuned models, illustrating the transfer of skills from synthetic to real task evaluations.
Our study highlights the potential of finetuning on synthetic data for improving the performance of LLMs on longer-context tasks.
- Score: 8.216001662843384
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent studies have shown that Large Language Models (LLMs) struggle to accurately retrieve information and maintain reasoning capabilities when processing long-context inputs. To address these limitations, we propose a finetuning approach utilizing a carefully designed synthetic dataset comprising numerical key-value retrieval tasks. Our experiments on models like GPT-3.5 Turbo and Mistral 7B demonstrate that finetuning LLMs on this dataset significantly improves LLMs' information retrieval and reasoning capabilities in longer-context settings. We present an analysis of the finetuned models, illustrating the transfer of skills from synthetic to real task evaluations (e.g., $10.5\%$ improvement on $20$ documents MDQA at position $10$ for GPT-3.5 Turbo). We also find that finetuned LLMs' performance on general benchmarks remains almost constant while LLMs finetuned on other baseline long-context augmentation data can encourage hallucination (e.g., on TriviaQA, Mistral 7B finetuned on our synthetic data cause no performance drop while other baseline data can cause a drop that ranges from $2.33\%$ to $6.19\%$). Our study highlights the potential of finetuning on synthetic data for improving the performance of LLMs on longer-context tasks.
Related papers
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts.
We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM.
We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
arXiv Detail & Related papers (2024-07-16T04:41:58Z) - DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity.
Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data.
Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
arXiv Detail & Related papers (2024-06-25T04:27:53Z) - Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models [89.88010750772413]
Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs)
Our work delves into these specific flaws associated with question-answer (Q-A) pairs, a prevalent type of synthetic data, and presents a method based on unlearning techniques to mitigate these flaws.
Our work has yielded key insights into the effective use of synthetic data, aiming to promote more robust and efficient LLM training.
arXiv Detail & Related papers (2024-06-18T08:38:59Z) - LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement [79.31084387589968]
Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks.
We propose LLM2LLM, a data augmentation strategy that uses a teacher LLM to enhance a small seed dataset.
We achieve improvements up to 24.2% on the GSM8K dataset, 32.6% on CaseHOLD, 32.0% on SNIPS, 52.6% on TREC and 39.8% on SST-2 over regular fine-tuning in the low-data regime.
arXiv Detail & Related papers (2024-03-22T08:57:07Z) - Automated Data Curation for Robust Language Model Fine-Tuning [13.8454385440986]
We introduce an automated data curation pipeline CLEAR for instruction tuning datasets.
CLEAR estimates which training data is low-quality and either filters or corrects it.
Experiments reveal that CLEAR consistently improves the performance of fine-tuned models across many datasets and models.
arXiv Detail & Related papers (2024-03-19T14:44:45Z) - Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN)
At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself.
This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
arXiv Detail & Related papers (2024-01-02T18:53:13Z) - Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges [3.130575840003799]
GPT-4 can be used to augment existing reading comprehension datasets.
This work serves to be the first analysis of LLMs as synthetic data augmenters for QA systems.
arXiv Detail & Related papers (2023-09-21T18:48:02Z) - Large Language Models as Data Preprocessors [10.914067455923847]
Large Language Models (LLMs), typified by OpenAI's GPT series and Meta's LLaMA variants, have marked a significant advancement in artificial intelligence.
This study expands on the applications of LLMs, exploring their potential in data preprocessing.
We propose an LLM-based framework for data preprocessing, which integrates cutting-edge prompt engineering techniques.
arXiv Detail & Related papers (2023-08-30T23:28:43Z) - Scaling Relationship on Learning Mathematical Reasoning with Large
Language Models [75.29595679428105]
We investigate how the pre-training loss, supervised data amount, and augmented data amount influence the reasoning performances of a supervised LLM.
We find that rejection samples from multiple models push LLaMA-7B to an accuracy of 49.3% on GSM8K which outperforms the supervised fine-tuning (SFT) accuracy of 35.9% significantly.
arXiv Detail & Related papers (2023-08-03T15:34:01Z)
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.