Fast-Slow Thinking for Large Vision-Language Model Reasoning
- URL: http://arxiv.org/abs/2504.18458v1
- Date: Fri, 25 Apr 2025 16:11:23 GMT
- Title: Fast-Slow Thinking for Large Vision-Language Model Reasoning
- Authors: Wenyi Xiao, Leilei Gan, Weilong Dai, Wanggui He, Ziwei Huang, Haoyuan Li, Fangxun Shu, Zhelun Yu, Peng Zhang, Hao Jiang, Fei Wu,
- Abstract summary: We present textbfFAST, a framework that adapts reasoning depth based on question characteristics.<n>FAST achieves state-of-the-art accuracy with over 10% relative improvement compared to the base model.
- Score: 22.084891053164686
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent advances in large vision-language models (LVLMs) have revealed an \textit{overthinking} phenomenon, where models generate verbose reasoning across all tasks regardless of questions. To address this issue, we present \textbf{FAST}, a novel \textbf{Fa}st-\textbf{S}low \textbf{T}hinking framework that dynamically adapts reasoning depth based on question characteristics. Through empirical analysis, we establish the feasibility of fast-slow thinking in LVLMs by investigating how response length and data distribution affect performance. We develop FAST-GRPO with three components: model-based metrics for question characterization, an adaptive thinking reward mechanism, and difficulty-aware KL regularization. Experiments across seven reasoning benchmarks demonstrate that FAST achieves state-of-the-art accuracy with over 10\% relative improvement compared to the base model, while reducing token usage by 32.7-67.3\% compared to previous slow-thinking approaches, effectively balancing reasoning length and accuracy.
Related papers
- Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following [10.119219532863767]
lazy reasoning during the thinking stage is the primary factor contributing to poor instruction adherence.<n>We propose a comprehensive framework designed to enable rigorous reasoning processes involving preview and self-checking.<n>Our Light-IF-32B model surpasses both larger open-source models such as DeepSeek-R1 and closed-source models like Doubao-1.6.
arXiv Detail & Related papers (2025-08-05T07:42:00Z) - Lost at the Beginning of Reasoning [82.18834329384514]
We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.<n>We introduce a new benchmark specifically constructed with deliberately flawed first reasoning steps to systematically evaluate model self-correction capabilities.
arXiv Detail & Related papers (2025-06-27T09:53:57Z) - ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation [53.149817480019834]
Recent advancements in large reasoning models (LRMs) have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT)<n>We propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely by injecting the textual hint during the token generation of the reasoning process.<n>Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning processes while maintaining performance well.
arXiv Detail & Related papers (2025-06-23T16:20:44Z) - Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
arXiv Detail & Related papers (2025-06-05T07:31:18Z) - Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning [36.470695895695044]
Self-Route is a dynamic reasoning framework that automatically selects between general and reasoning modes.<n>We show that Self-Route achieves comparable accuracy to reasoning models while reducing token consumption by 30-55%.
arXiv Detail & Related papers (2025-05-27T03:18:31Z) - LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling [29.721108461390973]
We introduce PIR (Perplexity-based Importance Refinement), a principled framework that quantitatively evaluates the importance of each reasoning step.<n>PIR identifies and selectively prunes only low-importance functional steps while preserving progressive reasoning components.<n>Our approach demonstrates strong generalizability across different model sizes, data sources, and token budgets.
arXiv Detail & Related papers (2025-05-25T15:17:57Z) - Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens [51.90059610606049]
This paper revisits the efficiency of such reasoning processes through an information-theoretic lens.<n>We propose two metrics, InfoBias and InfoGain, to quantify divergence from ideal reasoning paths and stepwise information contribution.<n>Motivated by these findings, we introduce an entropy-based Adaptive Think strategy that dynamically halts reasoning once confidence is sufficiently high.
arXiv Detail & Related papers (2025-05-23T13:38:56Z) - Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning [27.498043430208085]
Excessive reliance on chain-of-thought (CoT) reasoning can impair model performance.<n>We propose Certainty-based Adaptive Reasoning (CAR)<n>CAR switches between short answers and long-form reasoning based on the model perplexity.
arXiv Detail & Related papers (2025-05-21T06:20:17Z) - Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models [21.579319926212296]
Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks.<n>They struggle with temporal reasoning, which requires processing time-related information such as event sequencing, durations, and inter-temporal relationships.<n>We introduce TISER, a novel framework that enhances the temporal reasoning abilities of LLMs through a multi-stage process that combines timeline construction with iterative self-reflection.
arXiv Detail & Related papers (2025-04-07T16:51:45Z) - Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching [60.04718679054704]
Chain-of-Thought prompting elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs.<n>We propose Sketch-of-Thought (SoT), a prompting framework that integrates cognitively inspired reasoning paradigms with linguistic constraints.<n>SoT achieves token reductions of up to 78% with minimal accuracy loss across 15 reasoning datasets.
arXiv Detail & Related papers (2025-03-07T06:57:17Z) - LINGOLY-TOO: Disentangling Memorisation from Reasoning with Linguistic Templatisation and Orthographic Obfuscation [1.2576388595811496]
We introduce a framework for producing linguistic reasoning problems that reduces the effect of memorisation in model performance estimates.<n>We apply this framework to develop LINGOLY-TOO, a challenging benchmark for linguistic reasoning.
arXiv Detail & Related papers (2025-03-04T19:57:47Z) - Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning [113.49074603075032]
Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning tasks.<n>We explore whether scaling with longer CoTs can indeed impair the reasoning performance of Large Language Models (LLMs) in certain domains.
arXiv Detail & Related papers (2025-02-25T10:48:05Z) - Path-of-Thoughts: Extracting and Following Paths for Robust Relational Reasoning with Large Language Models [62.12031550252253]
We present Path-of-Thoughts (PoT), a novel framework designed to tackle relation reasoning.<n>PoT efficiently extracts a task-agnostic graph that identifies crucial entities, relations, and attributes within the problem context.<n>PoT identifies relevant reasoning chains within the graph corresponding to the posed question, facilitating inference of potential answers.
arXiv Detail & Related papers (2024-12-23T20:27:12Z) - Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance.
Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning.
Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
arXiv Detail & Related papers (2024-08-08T17:20:08Z) - Optimizing Language Model's Reasoning Abilities with Weak Supervision [48.60598455782159]
We present textscPuzzleBen, a weakly supervised benchmark that comprises 25,147 complex questions, answers, and human-generated rationales.
A unique aspect of our dataset is the inclusion of 10,000 unannotated questions, enabling us to explore utilizing fewer supersized data to boost LLMs' inference capabilities.
arXiv Detail & Related papers (2024-05-07T07:39:15Z) - Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.<n>However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
arXiv Detail & Related papers (2024-03-01T09:01:53Z) - RDR: the Recap, Deliberate, and Respond Method for Enhanced Language
Understanding [6.738409533239947]
The Recap, Deliberate, and Respond (RDR) paradigm addresses this issue by incorporating three distinct objectives within the neural network pipeline.
By cascading these three models, we mitigate the potential for gaming the benchmark and establish a robust method for capturing the underlying semantic patterns.
Our results demonstrate improved performance compared to competitive baselines, with an enhancement of up to 2% on standard metrics.
arXiv Detail & Related papers (2023-12-15T16:41:48Z) - Self-Convinced Prompting: Few-Shot Question Answering with Repeated
Introspection [13.608076739368949]
We introduce a novel framework that harnesses the potential of large-scale pre-trained language models.
Our framework processes the output of a typical few-shot chain-of-thought prompt, assesses the correctness of the response, scrutinizes the answer, and ultimately produces a new solution.
arXiv Detail & Related papers (2023-10-08T06:36:26Z) - A Causal Framework to Quantify the Robustness of Mathematical Reasoning
with Language Models [81.15974174627785]
We study the behavior of language models in terms of robustness and sensitivity to direct interventions in the input space.
Our analysis shows that robustness does not appear to continuously improve as a function of size, but the GPT-3 Davinci models (175B) achieve a dramatic improvement in both robustness and sensitivity compared to all other GPT variants.
arXiv Detail & Related papers (2022-10-21T15:12:37Z) - Confident Adaptive Language Modeling [95.45272377648773]
CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep.
We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
arXiv Detail & Related papers (2022-07-14T17:00:19Z) - Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap.
We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
arXiv Detail & Related papers (2021-09-09T10:10:29Z) - Non-Autoregressive Text Generation with Pre-trained Language Models [40.50508206201288]
We show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
We devise mechanisms to alleviate the two common problems of vanilla NAG models.
We propose a new decoding strategy, ratio-first, for applications where the output lengths can be approximately estimated beforehand.
arXiv Detail & Related papers (2021-02-16T15:30:33Z)
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.