X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

• URL: http://arxiv.org/abs/2603.24596v2
• Date: Mon, 30 Mar 2026 04:04:32 GMT
• Title: X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
• Abstract summary: X-OPD is a novel framework designed to align the capabilities of Speech LLMs to their text-based counterparts.<n>X-OPD significantly narrows the gap in complex tasks while preserving the model's inherent capabilities.
• Score: 30.665122798466015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts. The standard Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training methods fail to close this gap. To address this, we propose X-OPD, a novel Cross-Modal On-Policy Distillation framework designed to systematically align the capabilities of Speech LLMs to their text-based counterparts. X-OPD enables the Speech LLM to explore its own distribution via on-policy rollouts, where a text-based teacher model evaluates these trajectories and provides token-level feedback, effectively distilling teacher's capabilities into student's multi-modal representations. Extensive experiments across multiple benchmarks demonstrate that X-OPD significantly narrows the gap in complex tasks while preserving the model's inherent capabilities.

Related papers

• Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders [20.530146256745414]
  EPIC is a novel embedding-based in-context prompt training strategy for large language models.<n>It generates high-quality embeddings while reducing computational burden during both training and inference.
  arXiv  Detail & Related papers  (2026-05-02T10:31:01Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time [12.659582318581606]
  Current approaches, including Vision Foundation Models (VFMs) and Multimodal Large Language Models (MLLMs), enhance semantic understanding but suffer from high computational overhead and limited cross-domain transferability when fine-tuned.<n>We propose a novel framework employing Test-Time Scaling (TTS) that leverages vision-language alignment capabilities through Guidance-based methods for direct similarity scoring.<n>Our approach eliminates two-stage processing by employing structured prompts that generate length-controllable scoring outputs.
  arXiv  Detail & Related papers  (2025-09-02T09:25:13Z)
• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning [55.41828729623907]
  We present Writing-RL: an Adaptive Curriculum Reinforcement Learning framework to advance long-form writing capabilities beyond supervised fine-tuning.<n>The framework consists of three key components: Margin-aware Data Selection strategy that prioritizes samples with high learning potential, Pairwise Comparison Reward mechanism that provides discriminative learning signals, and Dynamic Reference Scheduling approach.
  arXiv  Detail & Related papers  (2025-06-06T05:40:39Z)
• Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration [15.711365331854614]
  We introduce Dynamic Adaptation of Reasoning Trajectories (DART), a novel data adaptation framework.<n>Instead of uniformly imitating expert steps, DART employs a selective imitation strategy guided by step-wise adaptability estimation.<n>We validate DART across multiple reasoning benchmarks and model scales, demonstrating that it significantly improves generalization and data efficiency.
  arXiv  Detail & Related papers  (2025-05-27T04:08:11Z)
• Integrating Visual Interpretation and Linguistic Reasoning for Math Problem Solving [61.992824291296444]
  Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs)<n>This paper proposes a paradigm shift: instead of training end-to-end vision-language reasoning models, we advocate for developing a decoupled reasoning framework.
  arXiv  Detail & Related papers  (2025-05-23T08:18:00Z)
• Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoring [0.0]
  This paper investigates the potentials of Large Language Models (LLMs) as adaptive tutors in the context of second-language learning.<n>We simulate full teacher-student dialogues in Spanish using instruction-tuned, open-source LLMs ranging in size from 7B to 12B parameters.<n>The output from the tutor model is then used to evaluate the effectiveness of CEFR-based prompting to control text difficulty across three proficiency levels.
  arXiv  Detail & Related papers  (2025-05-13T08:50:57Z)
• Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models [0.8133739801185272]
  The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) We propose the Self-refine Instruction-tuning method that elicits Smaller Language Models to self-refine their abilities. Results obtained on commonsense and math reasoning tasks show that this approach significantly outperforms Instruction-tuning in both in-domain and out-domain scenarios.
  arXiv  Detail & Related papers  (2024-05-01T09:10:27Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning [57.74233319453229]
  Large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task. We propose MultiCSR, a multi-level contrastive sentence representation learning framework that decomposes the process of prompting LLMs to generate a corpus. Our experiments reveal that MultiCSR enables a less advanced LLM to surpass the performance of ChatGPT, while applying it to ChatGPT achieves better state-of-the-art results.
  arXiv  Detail & Related papers  (2023-10-17T03:21:43Z)

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.