# Tackling Vision Language Tasks Through Learning Inner Monologues

arXiv: https://arxiv.org/abs/2308.09970 · HTML: https://mlsanity.com/paper/2308.09970/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 19 Aug 2023.

## Builds on (most cited first, 30 of 34)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages](https://mlsanity.com/paper/2305.04160/) (2023)
- [Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control](https://mlsanity.com/paper/1611.02796/) (2016)
- [ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions](https://mlsanity.com/paper/2303.06594/) (2023)
- [IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models](https://mlsanity.com/paper/2305.14985/) (2023)

## Built on by (most cited first, 7 of 7)

- [IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues](https://mlsanity.com/paper/2405.13021/) (2024)
- [IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT](https://mlsanity.com/paper/2404.02059/) (2024)
- [Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing](https://mlsanity.com/paper/2505.02811/) (2025)
- [Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models](https://mlsanity.com/paper/2309.04041/) (2023)
- [Right this way: Can VLMs Guide Us to See More to Answer Questions?](https://mlsanity.com/paper/2411.00394/) (2024)
- [GenIR: Generative Visual Feedback for Mental Image Retrieval](https://mlsanity.com/paper/2506.06220/) (2025)
- [Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection](https://mlsanity.com/paper/2610.05630/) (2026)

## Abstract (arXiv)

Visual language tasks require AI models to comprehend and reason with both visual and textual content. Driven by the power of Large Language Models (LLMs), two prominent methods have emerged: (1) the hybrid integration between LLMs and Vision-Language Models (VLMs), where visual inputs are firstly converted into language descriptions by VLMs, serving as inputs for LLMs to generate final answer(s); (2) visual feature alignment in language space, where visual inputs are encoded as embeddings and projected to LLMs' language space via further supervised fine-tuning. The first approach provides light training costs and interpretability but is hard to be optimized in an end-to-end fashion. The second approach presents decent performance, but feature alignment usually requires large amounts of training data and lacks interpretability. To tackle this dilemma, we propose a novel approach, Inner Monologue Multi-Modal Optimization (IMMO), to solve complex vision language problems by simulating inner monologue processes, a cognitive process in which an individual engages in silent verbal communication with themselves. We enable LLMs and VLMs to interact through natural language conversation and propose to use a two-stage training process to learn how to do the inner monologue (self-asking questions and answering questions). IMMO is evaluated on two popular tasks and the results suggest by emulating the cognitive phenomenon of internal dialogue, our approach can enhance reasoning and explanation abilities, contributing to the more effective fusion of vision and language models. More importantly, instead of using predefined human-crafted monologues, IMMO learns this process within the deep learning models, promising wider applicability to many different AI problems beyond vision language tasks.