InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback

• URL: http://arxiv.org/abs/2505.23950v1
• Date: Thu, 29 May 2025 19:00:42 GMT
• Title: InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
• Authors: Boyuan Chen, Donghai Hong, Jiaming Ji, Jiacheng Zheng, Bowen Dong, Jiayi Zhou, Kaile Wang, Juntao Dai, Xuyao Wang, Wenqi Chen, Qirui Zheng, Wenxin Li, Sirui Han, Yike Guo, Yaodong Yang,
• Abstract summary: A critical aspect of human learning is continuous interaction with the environment.<n>To move closer to human-level intelligence, models must support multi-turn, multimodal interaction.<n>We present an initial exploration through the InterMT -- the first preference dataset for multi-turn multimodal interaction.
• Score: 20.27708059361695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As multimodal large models (MLLMs) continue to advance across challenging tasks, a key question emerges: What essential capabilities are still missing? A critical aspect of human learning is continuous interaction with the environment -- not limited to language, but also involving multimodal understanding and generation. To move closer to human-level intelligence, models must similarly support multi-turn, multimodal interaction. In particular, they should comprehend interleaved multimodal contexts and respond coherently in ongoing exchanges. In this work, we present an initial exploration through the InterMT -- the first preference dataset for multi-turn multimodal interaction, grounded in real human feedback. In this exploration, we particularly emphasize the importance of human oversight, introducing expert annotations to guide the process, motivated by the fact that current MLLMs lack such complex interactive capabilities. InterMT captures human preferences at both global and local levels into nine sub-dimensions, consists of 15.6k prompts, 52.6k multi-turn dialogue instances, and 32.4k human-labeled preference pairs. To compensate for the lack of capability for multi-modal understanding and generation, we introduce an agentic workflow that leverages tool-augmented MLLMs to construct multi-turn QA instances. To further this goal, we introduce InterMT-Bench to assess the ability of MLLMs in assisting judges with multi-turn, multimodal tasks. We demonstrate the utility of \InterMT through applications such as judge moderation and further reveal the multi-turn scaling law of judge model. We hope the open-source of our data can help facilitate further research on aligning current MLLMs to the next step. Our project website can be found at https://pku-intermt.github.io .

Related papers

• Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models [8.08979200534563]
  Real-world applications demand sophisticated multi-turn interactions.<n>Recent advancements in large language models (LLMs) have revolutionized their ability to handle single-turn tasks.
  arXiv  Detail & Related papers  (2025-04-07T04:00:08Z)
• Low-rank Prompt Interaction for Continual Vision-Language Retrieval [47.323830129786145]
  We propose the Low-rank Prompt Interaction to address the problem of multi-modal understanding.<n>Considering that the training parameters scale to the number of layers and tasks, we propose low-rank interaction-augmented decomposition.<n>We also adopt hierarchical low-rank contrastive learning to ensure robustness training.
  arXiv  Detail & Related papers  (2025-01-24T10:00:47Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models [56.25156596019168]
  This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs) Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
  arXiv  Detail & Related papers  (2023-11-30T03:59:31Z)
• Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning [49.92517970237088]
  We tackle the problem of training a robot to understand multimodal prompts. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. We introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts.
  arXiv  Detail & Related papers  (2023-10-14T22:24:58Z)
• Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation [52.930183136111864]
  We propose using scorable negotiation to evaluate Large Language Models (LLMs) To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities. We provide procedures to create new games and increase games' difficulty to have an evolving benchmark.
  arXiv  Detail & Related papers  (2023-09-29T13:33:06Z)
• Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition [81.2011058113579]
  We argue that both the feature multimodality and conversational contextualization should be properly modeled simultaneously during the feature disentanglement and fusion steps. We propose a Contribution-aware Fusion Mechanism (CFM) and a Context Refusion Mechanism ( CRM) for multimodal and context integration. Our system achieves new state-of-the-art performance consistently.
  arXiv  Detail & Related papers  (2023-08-08T18:11:27Z)
• Chat with the Environment: Interactive Multimodal Perception Using Large Language Models [19.623070762485494]
  Large Language Models (LLMs) have shown remarkable reasoning ability in few-shot robotic planning. Our study demonstrates that LLMs can provide high-level planning and reasoning skills and control interactive robot behavior in a multimodal environment.
  arXiv  Detail & Related papers  (2023-03-14T23:01:27Z)
• On the Linguistic and Computational Requirements for Creating Face-to-Face Multimodal Human-Machine Interaction [0.0]
  We videorecorded thirty-four human-avatar interactions, performed complete linguistic microanalysis on video excerpts, and marked all the occurrences of multimodal actions and events. The data show evidence that double-loop feedback is established during a face-to-face conversation. We propose that knowledge from Conversation Analysis (CA), cognitive science, and Theory of Mind (ToM), among others, should be incorporated into the ones used for describing human-machine multimodal interactions.
  arXiv  Detail & Related papers  (2022-11-24T21:17:36Z)
• High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning [112.51498431119616]
  This paper studies efficient representation learning for high-modality scenarios involving a large set of diverse modalities. A single model, HighMMT, scales up to 10 modalities (text, image, audio, video, sensors, proprioception, speech, time-series, sets, and tables) and 15 tasks from 5 research areas.
  arXiv  Detail & Related papers  (2022-03-02T18:56:20Z)
• Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction [125.18248926508045]
  We propose Channel-Exchanging-Network (CEN) which is self-adaptive, parameter-free, and more importantly, applicable for both multimodal fusion and multitask learning. CEN dynamically exchanges channels betweenworks of different modalities. For the application of dense image prediction, the validity of CEN is tested by four different scenarios.
  arXiv  Detail & Related papers  (2021-12-04T05:47:54Z)

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.