Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
- URL: http://arxiv.org/abs/2407.11422v1
- Date: Tue, 16 Jul 2024 06:32:45 GMT
- Title: Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
- Authors: Jinrui Zhang, Teng Wang, Haigang Zhang, Ping Lu, Feng Zheng,
- Abstract summary: Large vision-language models (LVLMs) have shown promising performance on a variety of vision-language tasks.
They remain susceptible to hallucinations, generating outputs misaligned with visual content or instructions.
We propose reflective instruction tuning, which integrates rationale learning into visual instruction tuning.
- Score: 36.119299938503936
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large vision-language models (LVLMs) have shown promising performance on a variety of vision-language tasks. However, they remain susceptible to hallucinations, generating outputs misaligned with visual content or instructions. While various mitigation strategies have been proposed, they often neglect a key contributor to hallucinations: lack of fine-grained reasoning supervision during training. Without intermediate reasoning steps, models may establish superficial shortcuts between instructions and responses, failing to internalize the inherent reasoning logic. To address this challenge, we propose reflective instruction tuning, which integrates rationale learning into visual instruction tuning. Unlike previous methods that learning from responses only, our approach entails the model predicting rationales justifying why responses are correct or incorrect. This fosters a deeper engagement with the fine-grained reasoning underlying each response, thus enhancing the model's reasoning proficiency. To facilitate this approach, we propose REVERIE, the first large-scale instruction-tuning dataset with ReflEctiVE RatIonalE annotations. REVERIE comprises 115k machine-generated reasoning instructions, each meticulously annotated with a corresponding pair of correct and confusing responses, alongside comprehensive rationales elucidating the justification behind the correctness or erroneousness of each response. Experimental results on multiple LVLM benchmarks reveal that reflective instruction tuning with the REVERIE dataset yields noticeable performance gain over the baseline model, demonstrating the effectiveness of reflecting from the rationales. Project page is at https://zjr2000.github.io/projects/reverie.
Related papers
- Can Reasoning Help Large Language Models Capture Human Annotator Disagreement? [84.32752330104775]
Variation in human annotation (i.e., disagreements) is common in NLP.<n>We evaluate the influence of different reasoning settings on Large Language Model disagreement modeling.<n>Surprisingly, our results show that RLVR-style reasoning degrades performance in disagreement modeling.
arXiv Detail & Related papers (2025-06-24T09:49:26Z) - Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning [78.17782197231325]
We propose a reasoning-guided reinforcement learning strategy that aligns the extractor's captioning behavior with the reasoning objective.<n> Experiments on multi-modal math and science benchmarks show that the proposed RACRO method achieves state-of-the-art average performance.
arXiv Detail & Related papers (2025-06-05T02:28:07Z) - Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning [96.01617809845396]
Ground-R1 is a reinforcement learning framework that enables grounded visual reasoning without requiring explicit evidence or rationale annotations.<n>Ground-R1 achieves superior performance and exhibits emergent cognitive behaviors such as uncertainty awareness, spatial perception, and iterative refinement.
arXiv Detail & Related papers (2025-05-26T17:51:47Z) - Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning [16.86024541396427]
Re-Critic is a visual rationale synthesizer that augments raw instructions with rationale explanation.<n>Re-Critic employs an in-context self-critic mechanism to select response pairs for preference tuning.<n> Experiments demonstrate that models fine-tuned with our rationale-augmented dataset yield gains that extend beyond hallucination-specific tasks to broader multimodal reasoning tasks.
arXiv Detail & Related papers (2025-05-12T01:51:50Z) - OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)
We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.
OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
arXiv Detail & Related papers (2025-03-21T17:52:43Z) - GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training [62.536191233049614]
Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs)
This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld.
We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse.
arXiv Detail & Related papers (2025-03-11T15:17:02Z) - Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time [17.3254565018168]
Large Language Models (LLMs) often struggle with complex reasoning scenarios.
We introduce a contrastive reflection synthesis pipeline that enhances the accuracy and depth of LLM-generated reflections.
We propose a dual-model reasoning framework within a verbal reinforcement learning paradigm.
arXiv Detail & Related papers (2025-02-26T15:41:41Z) - 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) - Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness.
We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
arXiv Detail & Related papers (2024-10-21T17:00:06Z) - Revealing the Inherent Instructability of Pre-Trained Language Models [9.504992236994697]
We show that Response Tuning (RT) removes the instruction and its corresponding mapping to the response from instruction tuning.
Our experiments demonstrate that RT, trained only on responses, can effectively respond to a wide range of instructions and exhibit helpfulness approaching that of their instruction-tuned counterparts.
arXiv Detail & Related papers (2024-10-03T13:15:19Z) - Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs [52.497823009176074]
Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations.
We introduce Visual Description Grounded Decoding (VDGD), a training-free method designed to enhance visual perception and improve reasoning capabilities in LVLMs.
arXiv Detail & Related papers (2024-05-24T16:21:59Z) - FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback [16.24562885483636]
We propose an innovative method to align modalities in Large Vision-Language Models (LVLMs) through Fine-Grained Artificial Intelligence Feedback (FGAIF)
Specifically, we first utilize AI tools to predict the types of hallucination for each segment in the response and obtain a collection of fine-grained feedback. Then, based on the collected reward data, three specialized reward models are trained to produce dense rewards. Finally, a novel fine-grained feedback module is integrated into the Proximal Policy Optimization (PPO) algorithm.
arXiv Detail & Related papers (2024-04-07T19:00:45Z) - Debiasing Multimodal Large Language Models [61.6896704217147]
Large Vision-Language Models (LVLMs) have become indispensable tools in computer vision and natural language processing.
Our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior to the input image.
To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies.
arXiv Detail & Related papers (2024-03-08T12:35:07Z) - On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks [17.329365493094542]
We present a principled empirical study of the performance of GPT-4 in three domains: Game of 24, Graph Coloring, and STRIPS planning.
We observe significant performance collapse with self-critique and significant performance gains with sound external verification.
arXiv Detail & Related papers (2024-02-12T23:11:01Z) - Interpretable Visual Question Answering via Reasoning Supervision [4.76359068115052]
Transformer-based architectures have recently demonstrated remarkable performance in the Visual Question Answering (VQA) task.
We propose a novel architecture for visual question answering that leverages common sense reasoning as a supervisory signal.
We demonstrate both quantitatively and qualitatively that the proposed approach can boost the model's visual perception capability and lead to performance increase.
arXiv Detail & Related papers (2023-09-07T14:12:31Z) - Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models [81.01397924280612]
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations.
We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains.
arXiv Detail & Related papers (2023-04-23T13:54:39Z) - See, Think, Confirm: Interactive Prompting Between Vision and Language
Models for Knowledge-based Visual Reasoning [60.43585179885355]
We propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning.
IPVR contains three stages, see, think and confirm.
We conduct experiments on a range of knowledge-based visual reasoning datasets.
arXiv Detail & Related papers (2023-01-12T18:59:50Z)
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.