EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
- URL: http://arxiv.org/abs/2410.04571v1
- Date: Sun, 6 Oct 2024 18:06:42 GMT
- Title: EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
- Authors: Aakriti Agrawal, Mucong Ding, Zora Che, Chenghao Deng, Anirudh Satheesh, John Langford, Furong Huang,
- Abstract summary: We propose an innovative approach to weak-to-strong (w2s) generalization.
We show that weak models trained on simpler tasks collaboratively supervise stronger models on more complex tasks.
We observe an improvement of up to 14% over existing baselines and average improvements of 5% and 4% for binary classification and generative tasks.
- Score: 28.43206274079919
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: How can we harness the collective capabilities of multiple Large Language Models (LLMs) to create an even more powerful model? This question forms the foundation of our research, where we propose an innovative approach to weak-to-strong (w2s) generalization-a critical problem in AI alignment. Our work introduces an easy-to-hard (e2h) framework for studying the feasibility of w2s generalization, where weak models trained on simpler tasks collaboratively supervise stronger models on more complex tasks. This setup mirrors real-world challenges, where direct human supervision is limited. To achieve this, we develop a novel AdaBoost-inspired ensemble method, demonstrating that an ensemble of weak supervisors can enhance the performance of stronger LLMs across classification and generative tasks on difficult QA datasets. In several cases, our ensemble approach matches the performance of models trained on ground-truth data, establishing a new benchmark for w2s generalization. We observe an improvement of up to 14% over existing baselines and average improvements of 5% and 4% for binary classification and generative tasks, respectively. This research points to a promising direction for enhancing AI through collective supervision, especially in scenarios where labeled data is sparse or insufficient.
Related papers
- Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models [26.393123295267642]
Weak-to-Strong generalization (W2SG) is a new trend to elicit the full capabilities of a strong model with supervision from a weak model.<n>We fine-tune a strong model with trajectories of intermediate actions generated by a weak model.<n>Our empirical evaluations demonstrate substantial improvements in reasoning and decision-making capabilities across diverse task domains.
arXiv Detail & Related papers (2025-07-25T00:17:09Z) - EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles [32.189105375228294]
We propose a novel method aimed at improving weak experts, by training on the same limited human-level data, enabling them to generalize to complex, super-human-level tasks.<n>Our approach, called textbfEnsemW2S, employs a token-level ensemble strategy that iteratively combines multiple weak experts.<n>We extensively evaluate the generalization performance of both the ensemble of weak experts and the subsequent strong student model across in-distribution (ID) and out-of-distribution (OOD) datasets.
arXiv Detail & Related papers (2025-05-28T04:23:12Z) - MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models [34.138699712315]
This paper introduces a novel vision--action (VLA) model, mixture of robotic experts (MoRE) for quadruped robots.
MoRE integrates multiple low-rank adaptation modules as distinct experts within a dense multi-modal large language model.
Experiments demonstrate that MoRE outperforms all baselines across six different skills and exhibits superior generalization capabilities in out-of-distribution scenarios.
arXiv Detail & Related papers (2025-03-11T03:13:45Z) - Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution [66.11004226578771]
Existing robust benchmark datasets have two key limitations.<n>They generate only a limited range of perturbations for a single Information Extraction (IE) task.<n>Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench.<n>We show that training with only textbf15% of the data leads to an average textbf7.5% relative performance improvement across three IE tasks.
arXiv Detail & Related papers (2025-03-05T05:39:29Z) - Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.
However, they still struggle with problems requiring multi-step decision-making and environmental feedback.
We propose a framework that can automatically learn a reward model from the environment without human annotations.
arXiv Detail & Related papers (2025-02-17T18:49:25Z) - Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.
Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.
We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
arXiv Detail & Related papers (2025-02-04T17:26:58Z) - Unconstrained Model Merging for Enhanced LLM Reasoning [42.079040543428036]
We explore the potential of merging multiple expert models into a single large language model.
We propose an unconstrained model merging framework that accommodates both homogeneous and heterogeneous model architectures.
Across 7 benchmarks and 9 reasoning-optimized LLMs, we reveal key findings that reasoning emerges from merging.
arXiv Detail & Related papers (2024-10-17T16:04:07Z) - NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks.
We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities.
We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
arXiv Detail & Related papers (2024-09-17T17:59:06Z) - Weak-to-Strong Reasoning [33.20094938292376]
We introduce a progressive learning framework that enables the strong model to autonomously refine its training data.
Our method significantly enhances the reasoning capabilities of Llama2-70b using three separate weak models.
This work paves the way for a more scalable and sophisticated strategy to enhance AI reasoning powers.
arXiv Detail & Related papers (2024-07-18T16:25:17Z) - Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios.
We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples.
Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
arXiv Detail & Related papers (2024-06-07T11:37:45Z) - Vision Superalignment: Weak-to-Strong Generalization for Vision
Foundation Models [55.919653720979824]
This paper focuses on the concept of weak-to-strong generalization, which involves using a weaker model to supervise a stronger one.
We introduce a novel and adaptively adjustable loss function for weak-to-strong supervision.
Our approach not only exceeds the performance benchmarks set by strong-to-strong generalization but also surpasses the outcomes of fine-tuning strong models with whole datasets.
arXiv Detail & Related papers (2024-02-06T06:30:34Z) - A General Framework for Learning from Weak Supervision [93.89870459388185]
This paper introduces a general framework for learning from weak supervision (GLWS) with a novel algorithm.
Central to GLWS is an Expectation-Maximization (EM) formulation, adeptly accommodating various weak supervision sources.
We also present an advanced algorithm that significantly simplifies the EM computational demands.
arXiv Detail & Related papers (2024-02-02T21:48:50Z) - Improving Weak-to-Strong Generalization with Scalable Oversight and
Ensemble Learning [21.401598876308345]
This paper presents a follow-up study to OpenAI's recent superalignment work on Weak-to-Strong Generalization (W2SG)
Superalignment focuses on ensuring that high-level AI systems remain consistent with human values and intentions when dealing with complex, high-risk tasks.
Our study simulates two phases of superalignment under the W2SG framework: the development of general superhuman models and the progression towards superintelligence.
arXiv Detail & Related papers (2024-02-01T15:30:19Z) - Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs [13.262711792955377]
This study explores the effectiveness of Large Language Models (LLMs) for automated essay scoring.
We propose an open-source LLM-based AES system, inspired by the dual-process theory.
We find that our system not only automates the grading process but also enhances the performance and efficiency of human graders.
arXiv Detail & Related papers (2024-01-12T07:50:10Z) - Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset.
We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
arXiv Detail & Related papers (2024-01-11T17:56:59Z) - Improving Generalization of Alignment with Human Preferences through
Group Invariant Learning [56.19242260613749]
Reinforcement Learning from Human Feedback (RLHF) enables the generation of responses more aligned with human preferences.
Previous work shows that Reinforcement Learning (RL) often exploits shortcuts to attain high rewards and overlooks challenging samples.
We propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
arXiv Detail & Related papers (2023-10-18T13:54:15Z) - SALMON: Self-Alignment with Instructable Reward Models [80.83323636730341]
This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision.
We develop an AI assistant named Dromedary-2 with only 6 exemplars for in-context learning and 31 human-defined principles.
arXiv Detail & Related papers (2023-10-09T17:56:53Z) - Improving Open Information Extraction with Large Language Models: A
Study on Demonstration Uncertainty [52.72790059506241]
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text.
Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
arXiv Detail & Related papers (2023-09-07T01:35:24Z) - Sparse MoEs meet Efficient Ensembles [49.313497379189315]
We study the interplay of two popular classes of such models: ensembles of neural networks and sparse mixture of experts (sparse MoEs)
We present Efficient Ensemble of Experts (E$3$), a scalable and simple ensemble of sparse MoEs that takes the best of both classes of models, while using up to 45% fewer FLOPs than a deep ensemble.
arXiv Detail & Related papers (2021-10-07T11:58:35Z) - CorDEL: A Contrastive Deep Learning Approach for Entity Linkage [70.82533554253335]
Entity linkage (EL) is a critical problem in data cleaning and integration.
With the ever-increasing growth of new data, deep learning (DL) based approaches have been proposed to alleviate the high cost of EL associated with the traditional models.
We argue that the twin-network architecture is sub-optimal to EL, leading to inherent drawbacks of existing models.
arXiv Detail & Related papers (2020-09-15T16:33:05Z)
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.