Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
- URL: http://arxiv.org/abs/2408.10613v2
- Date: Thu, 12 Dec 2024 03:24:29 GMT
- Title: Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
- Authors: Guangyuan Ma, Yongliang Ma, Xing Wu, Zhenpeng Su, Ming Zhou, Songlin Hu,
- Abstract summary: We propose a new task-level Distributionally Robust Optimization (tDRO) algorithm for Large Language Model-based Dense Retrieval fine-tuning.
The tDRO parameterizes the domain weights and updates them with scaled domain gradients.
Experiments show optimal improvements in large-scale retrieval benchmarks and reduce up to 30% dataset usage.
- Score: 32.104911827710936
- License:
- Abstract: Large Language Model-based Dense Retrieval (LLM-DR) optimizes over numerous heterogeneous fine-tuning collections from different domains. However, the discussion about its training data distribution is still minimal. Previous studies rely on empirically assigned dataset choices or sampling ratios, which inevitably lead to sub-optimal retrieval performances. In this paper, we propose a new task-level Distributionally Robust Optimization (tDRO) algorithm for LLM-DR fine-tuning, targeted at improving the universal domain generalization ability by end-to-end reweighting the data distribution of each task. The tDRO parameterizes the domain weights and updates them with scaled domain gradients. The optimized weights are then transferred to the LLM-DR fine-tuning to train more robust retrievers. Experiments show optimal improvements in large-scale retrieval benchmarks and reduce up to 30% dataset usage after applying our optimization algorithm with a series of different-sized LLM-DR models.
Related papers
- DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization [61.492590008258986]
Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs.
We propose DRPruning, which incorporates distributionally robust optimization to restore balanced performance across domains.
arXiv Detail & Related papers (2024-11-21T12:02:39Z) - Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach [51.76826149868971]
Policy evaluation via Monte Carlo simulation is at the core of many MC Reinforcement Learning (RL) algorithms.
We propose as a quality index a surrogate of the mean squared error of a return estimator that uses trajectories of different lengths.
We present an adaptive algorithm called Robust and Iterative Data collection strategy Optimization (RIDO)
arXiv Detail & Related papers (2024-10-17T11:47:56Z) - Ordinal Preference Optimization: Aligning Human Preferences via NDCG [28.745322441961438]
We develop an end-to-end preference optimization algorithm by approxing NDCG with a differentiable surrogate loss.
OPO outperforms existing pairwise and listwise approaches on evaluation sets and general benchmarks like AlpacaEval.
arXiv Detail & Related papers (2024-10-06T03:49:28Z) - Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss.
The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
arXiv Detail & Related papers (2024-09-26T12:37:26Z) - Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models [0.8399688944263842]
Large Language Models (LLMs) have the capability to understand and generate human-like text from input queries.
This study extends this concept to the integration of LLMs within Retrieval-Augmented Generation (RAG) pipelines.
We evaluate the impact of fine-tuning on the LLMs' capacity for data extraction and contextual understanding.
arXiv Detail & Related papers (2024-06-17T04:35:17Z) - Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs.
We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention.
Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
arXiv Detail & Related papers (2024-06-12T16:58:41Z) - Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions.
Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
arXiv Detail & Related papers (2024-05-29T17:59:07Z) - Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
We introduce a novel closed-form formulation for direct preference optimization using multiple reference models.
The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models.
Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
arXiv Detail & Related papers (2024-05-26T00:29:04Z) - Low-Rank Representations Meets Deep Unfolding: A Generalized and
Interpretable Network for Hyperspectral Anomaly Detection [41.50904949744355]
Current hyperspectral anomaly detection (HAD) benchmark datasets suffer from low resolution, simple background, and small size of the detection data.
These factors also limit the performance of the well-known low-rank representation (LRR) models in terms of robustness.
We build a new set of HAD benchmark datasets for improving the robustness of the HAD algorithm in complex scenarios, AIR-HAD for short.
arXiv Detail & Related papers (2024-02-23T14:15:58Z) - MLLM-DataEngine: An Iterative Refinement Approach for MLLM [62.30753425449056]
We propose a novel closed-loop system that bridges data generation, model training, and evaluation.
Within each loop, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results.
For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data.
For quality, we resort to GPT-4 to generate high-quality data with each given data type.
arXiv Detail & Related papers (2023-08-25T01:41:04Z) - Towards Optimization and Model Selection for Domain Generalization: A
Mixup-guided Solution [43.292274574847234]
We propose Mixup guided optimization and selection techniques for domain generalization.
For optimization, we utilize an out-of-distribution dataset that can guide the preference direction.
For model selection, we generate a validation dataset with a closer distance to the target distribution.
arXiv Detail & Related papers (2022-09-01T02:18:00Z)
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.