GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems

• URL: http://arxiv.org/abs/2606.21097v2
• Date: Wed, 24 Jun 2026 18:58:43 GMT
• Title: GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems
• Abstract summary: Current training paradigms treat personalization and grounding as a single monolithic learning problem.<n>We propose the Generic Response-Augmented Generation (GRAG) framework that decouples these competing objectives.<n>GRAG significantly outperforms state-of-the-art methods that do not use auxiliary scaffolding.
• Score: 1.973963382480151
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge. We identify a fundamental bottleneck in the existing approaches: current training paradigms treat personalization and grounding as a single monolithic learning problem. Under these paradigms, language models are forced to simultaneously address what to say (content grounding) and how to say it in a user-specific way (personalization), which introduces significant computational and optimization challenges. Consequently, contextual grounding is often sacrificed for persona adherence, or vice versa, resulting in responses that are either weakly grounded in the conversational history or insufficiently personalized. In this work, we propose the Generic Response-Augmented Generation (GRAG) framework that decouples these competing objectives by leveraging offline, generic responses from high-capacity, general-purpose LLMs as a semantic and structural scaffold to guide the fine-tuning of smaller, task-specialized models seamlessly in resource-limited environments. By decoupling the content grounding from personalization, GRAG allows the model to focus exclusively on persona injection while remaining firmly anchored to the conversational context. We instantiate the GRAG in two post- and pre-fusion-based architectural variants and evaluate them on multiple benchmark conversational datasets that cover diverse personalization structures. Our results demonstrate that GRAG significantly outperforms state-of-the-art methods that do not use auxiliary scaffolding, yielding up to 47% improvements in ROUGE-2 and 36% in BLEU scores. Ultimately, GRAG offers a generalizable blueprint for building grounding-aware personalized conversational systems in resource-limited environments.

Related papers

• OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following [59.53720386342017]
  We propose a unified vision-language framework that adapts foundational Vision-Language Models for scalable multi-person gaze reasoning.<n>By modeling all individuals, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning.
  arXiv  Detail & Related papers  (2026-05-26T00:08:06Z)
• Sparse Personalized Text Generation with Multi-Trajectory Reasoning [95.19317487799292]
  PAT (Personalization with Aligned Trajectories) is a reasoning framework for cold-start LLM personalization.<n>It first retrieves information along two complementary trajectories: writing-style cues from stylistically similar users and topic-specific context from preference-aligned users.<n>It then employs a reinforcement learning-based, iterative dual-reasoning mechanism that enables the LLM to jointly refine and integrate these signals.
  arXiv  Detail & Related papers  (2026-04-27T20:58:49Z)
• Generation-Augmented Generation: A Plug-and-Play Framework for Private Knowledge Injection in Large Language Models [48.65910216527897]
  Generation-Augmented Generation (GAG) treats private expertise as an additional expert modality and injects it via a compact representation-level interface.<n>GAG improves specialist performance over strong RAG baselines by 15.34% and 14.86% on two benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T04:23:36Z)
• Personalized Vision via Visual In-Context Learning [62.85784251383279]
  We present a visual in-context learning framework for personalized vision.<n>PICO infers the underlying transformation and applies it to new inputs without retraining.<n>We also propose an attention-guided seed scorer that improves reliability via efficient inference scaling.
  arXiv  Detail & Related papers  (2025-09-29T17:58:45Z)
• Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data [17.614395125762304]
  Grounding language in perception and action is a key challenge when building situated agents that can interact with humans, or other agents, via language.<n>We propose Ground-Compose-Reinforce, an end-to-end, neurosymbolic framework for training RL agents directly from high-level task specifications.
  arXiv  Detail & Related papers  (2025-07-14T19:05:15Z)
• ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant [16.253265097323432]
  We present a new dataset named ReGraP, consisting of 120 sets of personalized knowledge.<n>We propose ReGraP-LLaVA, an MLLM trained with the corresponding KGs and CoT QA pairs.<n>Results show that the proposed model not only learns personalized knowledge but also performs relational reasoning in responses.
  arXiv  Detail & Related papers  (2025-05-06T16:00:13Z)
• A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation [29.348053519918928]
  We propose a novel stack-propagation framework for learning a dialogue generation and understanding pipeline. The proposed framework can benefit from the stacked encoder and decoders to learn from much smaller personalized dialogue data.
  arXiv  Detail & Related papers  (2024-10-26T13:09:21Z)
• Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation [69.01029651113386]
  Embodied-RAG is a framework that enhances the model of an embodied agent with a non-parametric memory system.<n>At its core, Embodied-RAG's memory is structured as a semantic forest, storing language descriptions at varying levels of detail.<n>We demonstrate that Embodied-RAG effectively bridges RAG to the robotics domain, successfully handling over 250 explanation and navigation queries.
  arXiv  Detail & Related papers  (2024-09-26T21:44:11Z)
• Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification [49.41632476658246]
  We discuss the extension of DFKD to Vision-Language Foundation Models without access to the billion-level image-text datasets. The objective is to customize a student model for distribution-agnostic downstream tasks with given category concepts. We propose three novel Prompt Diversification methods to encourage image synthesis with diverse styles.
  arXiv  Detail & Related papers  (2024-07-21T13:26:30Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)

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.