CTPD: Cross Tokenizer Preference Distillation

• URL: http://arxiv.org/abs/2601.11865v1
• Date: Sat, 17 Jan 2026 01:11:35 GMT
• Title: CTPD: Cross Tokenizer Preference Distillation
• Authors: Truong Nguyen, Phi Van Dat, Ngan Nguyen, Linh Ngo Van, Trung Le, Thanh Hong Nguyen,
• Abstract summary: Cross-Tokenizer Preference Distillation (CTPD) is the first unified framework for transferring human-aligned behavior between models with heterogeneous tokenizers.<n>CTPD introduces three key innovations: (1) Aligned Span Projection, which maps teacher and student to shared character-level spans for precise supervision transfer; (2) a cross-tokenizer adaptation of Token-level Importance Sampling (TIS-DPO) for improved credit assignment; and (3) a Teacher-Anchored Reference, allowing the student to directly leverage the teacher's preferences in a DPO-style objective.
• Score: 19.4149691480574
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplored, particularly in the more realistic cross-tokenizer setting. The incompatibility of tokenization schemes between teacher and student models has largely prevented fine-grained, white-box distillation of preference information. To address this gap, we propose Cross-Tokenizer Preference Distillation (CTPD), the first unified framework for transferring human-aligned behavior between models with heterogeneous tokenizers. CTPD introduces three key innovations: (1) Aligned Span Projection, which maps teacher and student tokens to shared character-level spans for precise supervision transfer; (2) a cross-tokenizer adaptation of Token-level Importance Sampling (TIS-DPO) for improved credit assignment; and (3) a Teacher-Anchored Reference, allowing the student to directly leverage the teacher's preferences in a DPO-style objective. Our theoretical analysis grounds CTPD in importance sampling, and experiments across multiple benchmarks confirm its effectiveness, with significant performance gains over existing methods. These results establish CTPD as a practical and general solution for preference distillation across diverse tokenization schemes, opening the door to more accessible and efficient alignment of language models.

Related papers

• From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance [20.096802351171377]
  e-commerce search systems face strict latency requirements that prevent the direct application of Large Language Models.<n>We propose a two-stage reasoning distillation framework to transfer reasoning capabilities from a powerful teacher LLM to a lightweight, deployment-friendly student model.<n>Our framework achieves significant improvements across multiple metrics, validating its effectiveness and practical value.
  arXiv  Detail & Related papers  (2025-10-13T06:46:43Z)
• Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching [16.385782508179364]
  Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM.<n>Current distillation methods require similar tokenizers between the teacher and the student, restricting their applicability to only a small subset of teacher-student pairs.<n>We develop a principled cross-tokenizer distillation method to solve this crucial deficiency.<n>Our method is the first to enable effective distillation across fundamentally different tokenizers, while also substantially outperforming prior methods in all other cases.
  arXiv  Detail & Related papers  (2025-03-25T21:44:10Z)
• Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models [22.613040767122225]
  We propose a Preference-Aligned Distillation framework, which models teacher's preference knowledge as a probability distribution over all potential preferences.<n>Experiments on four mainstream alignment benchmarks demonstrate that PAD consistently and significantly outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-02-20T05:18:23Z)
• Adversarial Prompt Distillation for Vision-Language Models [61.39214202062028]
  Adversarial Prompt Tuning (APT) applies adversarial training during the process of prompt tuning.<n>APD is a bimodal knowledge distillation framework that enhances APT by integrating it with multi-modal knowledge transfer.<n>Extensive experiments on multiple benchmark datasets demonstrate the superiority of our APD method over the current state-of-the-art APT methods.
  arXiv  Detail & Related papers  (2024-11-22T03:02:13Z)
• Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition [58.41784639847413]
  Human emotion is a complex phenomenon conveyed and perceived through facial expressions, vocal tones, body language, and physiological signals. In this paper, a multi-teacher PKD (MT-PKDOT) method with self-distillation is introduced to align diverse teacher representations before distilling them to the student. Results indicate that our proposed method can outperform SOTA PKD methods.
  arXiv  Detail & Related papers  (2024-08-16T22:11:01Z)
• Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport [46.91791643660991]
  Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments. These models struggle in the wild because of the unavailability and quality of modalities used for training. In practice, only a subset of the training-time modalities may be available at test time. Learning with privileged information enables models to exploit data from additional modalities that are only available during training.
  arXiv  Detail & Related papers  (2024-01-27T19:44:15Z)
• On the Role of Bidirectionality in Language Model Pre-Training [85.14614350372004]
  We study the role of bidirectionality in next token prediction, text infilling, zero-shot priming and fine-tuning. We train models with up to 6.7B parameters, and find differences to remain consistent at scale.
  arXiv  Detail & Related papers  (2022-05-24T02:25:05Z)
• Learning What Not to Segment: A New Perspective on Few-Shot Segmentation [63.910211095033596]
  Recently few-shot segmentation (FSS) has been extensively developed. This paper proposes a fresh and straightforward insight to alleviate the problem. In light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting.
  arXiv  Detail & Related papers  (2022-03-15T03:08:27Z)
• Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation [34.441349114336994]
  We propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors. RM takes the rank of candidate boxes from teachers as a new form of knowledge to distill. PFI attempts to correlate feature differences with prediction differences, making feature imitation directly help to improve the student's accuracy.
  arXiv  Detail & Related papers  (2021-12-09T11:19:15Z)
• Contrastive Distillation on Intermediate Representations for Language Model Compression [89.31786191358802]
  We propose Contrastive Distillation on Intermediate Representations (CoDIR) as a principled knowledge distillation framework. By learning to distinguish positive sample from a large set of negative samples, CoDIR facilitates the student's exploitation of rich information in teacher's hidden layers. CoDIR can be readily applied to compress large-scale language models in both pre-training and finetuning stages, and achieves superb performance on the GLUE benchmark.
  arXiv  Detail & Related papers  (2020-09-29T17:31:43Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)

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.