Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
- URL: http://arxiv.org/abs/2311.14109v2
- Date: Wed, 3 Jul 2024 02:56:47 GMT
- Title: Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
- Authors: Cheng Tan, Jingxuan Wei, Zhangyang Gao, Linzhuang Sun, Siyuan Li, Ruifeng Guo, Bihui Yu, Stan Z. Li,
- Abstract summary: Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions.
Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning framework.
We propose MC-CoT, a self-consistency training strategy that generates multiple rationales and answers, subsequently selecting the most accurate through a voting process.
- Score: 49.3242278912771
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning framework, separating rationale generation from answer inference. However, these approaches often fall short due to the inadequate quality of the generated rationales. In this work, we delve into the importance of rationales in model reasoning. We observe that when rationales are completely accurate, the model's accuracy significantly improves, highlighting the need for high-quality rationale generation. Motivated by this, we propose MC-CoT, a self-consistency training strategy that generates multiple rationales and answers, subsequently selecting the most accurate through a voting process. This approach not only enhances the quality of generated rationales but also leads to more accurate and robust answers. Through extensive experiments, we demonstrate that our approach significantly improves model performance across various benchmarks. Remarkably, we show that even smaller base models, when equipped with our proposed approach, can achieve results comparable to those of larger models, illustrating the potential of our approach in harnessing the power of rationales for improved multimodal reasoning. The code is available at https://github.com/chengtan9907/mc-cot.
Related papers
- Vision-Language Models Can Self-Improve Reasoning via Reflection [20.196406628954303]
Chain-of-thought (CoT) has proven to improve the reasoning capability of large language models (LLMs)
We propose a self-training framework, R3V, which iteratively enhances the model's Vision-language Reasoning by Reflecting on CoT Rationales.
Our approach supports self-reflection on generated solutions, further boosting performance through test-time computation.
arXiv Detail & Related papers (2024-10-30T14:45:00Z) - Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models [63.36637269634553]
We present a novel method of further improving performance by requiring models to compare multiple reasoning chains.
We find that instruction tuning on DCoT datasets boosts the performance of even smaller, and therefore more accessible, language models.
arXiv Detail & Related papers (2024-07-03T15:01:18Z) - Brainstorming Brings Power to Large Language Models of Knowledge Reasoning [17.14501985068287]
Large Language Models (LLMs) have demonstrated amazing capabilities in language generation, text comprehension, and knowledge reasoning.
Recent studies have further improved the model's reasoning ability on a wide range of tasks by introducing multi-model collaboration.
We propose the multi-model brainstorming based on prompt. It incorporates different models into a group for brainstorming, and after multiple rounds of reasoning elaboration and re-inference, a consensus answer is reached.
arXiv Detail & Related papers (2024-06-02T14:47:14Z) - Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning)
The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs.
It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
arXiv Detail & Related papers (2024-05-31T14:23:49Z) - Improving Language Model Reasoning with Self-motivated Learning [60.779625789039486]
textitSelf-motivated Learning framework motivates the model itself to automatically generate rationales on existing datasets.
We train a reward model with the rank to evaluate the quality of rationales, and improve the performance of reasoning through reinforcement learning.
arXiv Detail & Related papers (2024-04-10T14:05:44Z) - Conceptual and Unbiased Reasoning in Language Models [98.90677711523645]
We propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions.
We show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks.
We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making.
arXiv Detail & Related papers (2024-03-30T00:53:53Z) - How Ambiguous are the Rationales for Natural Language Reasoning? A Simple Approach to Handling Rationale Uncertainty [0.0]
Rationales behind answers not only explain model decisions but boost language models to reason well on complex reasoning tasks.
It is non-trivial to estimate the degree to which the rationales are faithful enough to encourage model performance.
We propose how to deal with imperfect rationales causing aleatoric uncertainty.
arXiv Detail & Related papers (2024-02-22T07:12:34Z) - Reasoning Circuits: Few-shot Multihop Question Generation with
Structured Rationales [11.068901022944015]
Chain-of-thought rationale generation has been shown to improve performance on multi-step reasoning tasks.
We introduce a new framework for applying chain-of-thought inspired structured rationale generation to multi-hop question generation under a very low supervision regime.
arXiv Detail & Related papers (2022-11-15T19:36:06Z) - Why do you think that? Exploring Faithful Sentence-Level Rationales
Without Supervision [60.62434362997016]
We propose a differentiable training-framework to create models which output faithful rationales on a sentence level.
Our model solves the task based on each rationale individually and learns to assign high scores to those which solved the task best.
arXiv Detail & Related papers (2020-10-07T12:54:28Z)
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.