TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation

• URL: http://arxiv.org/abs/2505.20016v1
• Date: Mon, 26 May 2025 14:06:02 GMT
• Title: TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation
• Authors: Chengrui Huang, Shen Gao, Zhengliang Shi, Dongsheng Wang, Shuo Shang,
• Abstract summary: Token-level Tool-use Preference Alignment Training Framework (TTPA)<n>TTPA is a training paradigm for constructing token-level tool-use preference datasets.
• Score: 27.71948796412585
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing tool-learning methods usually rely on supervised fine-tuning, they often overlook fine-grained optimization of internal tool call details, leading to limitations in preference alignment and error discrimination. To overcome these challenges, we propose Token-level Tool-use Preference Alignment Training Framework (TTPA), a training paradigm for constructing token-level tool-use preference datasets that align LLMs with fine-grained preferences using a novel error-oriented scoring mechanism. TTPA first introduces reversed dataset construction, a method for creating high-quality, multi-turn tool-use datasets by reversing the generation flow. Additionally, we propose Token-level Preference Sampling (TPS) to capture fine-grained preferences by modeling token-level differences during generation. To address biases in scoring, we introduce the Error-oriented Scoring Mechanism (ESM), which quantifies tool-call errors and can be used as a training signal. Extensive experiments on three diverse benchmark datasets demonstrate that TTPA significantly improves tool-using performance while showing strong generalization ability across models and datasets.

Related papers

• Towards Efficient and Effective Alignment of Large Language Models [7.853945494882636]
  Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge.<n>This thesis advances LLM alignment by introducing novel methodologies in data collection, training, and evaluation.
  arXiv  Detail & Related papers  (2025-06-11T02:08:52Z)
• Aligning Instruction Tuning with Pre-training [81.4748965653345]
  We propose Aligning Instruction Tuning with Pre-training (AITP) to align instruction tuning with pre-training distributions.<n>We show consistent performance improvements with AITP on three fully open large language models (LLMs) across eight benchmarks.
  arXiv  Detail & Related papers  (2025-01-16T08:27:40Z)
• Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting [107.4034346788744]
  Existing vehicle trajectory prediction models struggle with generalizability, prediction uncertainties, and handling complex interactions.<n>We propose Perceiver with Register queries (PerReg+), a novel trajectory prediction framework that introduces: (1) Dual-Level Representation Learning via Self-Distillation (SD) and Masked Reconstruction (MR), capturing global context and fine-grained details; (2) Enhanced Multimodality using register-based queries and pretraining, eliminating the need for clustering and suppression; and (3) Adaptive Prompt Tuning during fine-tuning, freezing the main architecture and optimizing a small number of prompts for efficient adaptation.
  arXiv  Detail & Related papers  (2025-01-08T20:11:09Z)
• TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use [46.20445033086643]
  Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with external environments.<n>Standard supervised fine-tuning approach, which relies on large-scale datasets, often overlooks task-specific characteristics in tool use.<n>We propose TL-Training, a task-feature-based framework that mitigates the effects of suboptimal training data.
  arXiv  Detail & Related papers  (2024-12-20T02:21:36Z)
• ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning [29.001249598245]
  We introduce Reward-Oriented inStruction data sElection to optimize data selection for task-specific instruction tuning.<n> ROSE adapts an influence formulation to approximate the influence of training data points relative to a few-shot preference validation set to select the most task-related training data points.
  arXiv  Detail & Related papers  (2024-12-01T01:01:09Z)
• Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization [14.50339880957898]
  We aim to improve the preference optimization pipeline by taking a closer look at preference data generation and training regularization techniques. For preference data generation, we propose an iterative pairwise ranking mechanism that derives preference ranking of completions using pairwise comparison signals. For training regularization, we observe that preference optimization tends to achieve better convergence when the LLM predicted likelihood of preferred samples gets slightly reduced.
  arXiv  Detail & Related papers  (2024-11-07T23:03:11Z)
• A CLIP-Powered Framework for Robust and Generalizable Data Selection [51.46695086779598]
  Real-world datasets often contain redundant and noisy data, imposing a negative impact on training efficiency and model performance.<n>Data selection has shown promise in identifying the most representative samples from the entire dataset.<n>We propose a novel CLIP-powered data selection framework that leverages multimodal information for more robust and generalizable sample selection.
  arXiv  Detail & Related papers  (2024-10-15T03:00:58Z)
• Distributionally robust self-supervised learning for tabular data [2.942619386779508]
  Learning robust representation in presence of error slices is challenging, due to high cardinality features and the complexity of constructing error sets.<n>Traditional robust representation learning methods are largely focused on improving worst group performance in supervised setting in computer vision.<n>Our approach utilizes an encoder-decoder model trained with Masked Language Modeling (MLM) loss to learn robust latent representations.
  arXiv  Detail & Related papers  (2024-10-11T04:23:56Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• One-Shot Learning as Instruction Data Prospector for Large Language Models [108.81681547472138]
  textscNuggets uses one-shot learning to select high-quality instruction data from extensive datasets. We show that instruction tuning with the top 1% of examples curated by textscNuggets substantially outperforms conventional methods employing the entire dataset.
  arXiv  Detail & Related papers  (2023-12-16T03:33:12Z)
• Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations [89.86495158918615]
  Spurious correlations pose a major challenge for robust machine learning.<n>Models trained with empirical risk minimization (ERM) may learn to rely on correlations between class labels and spurious attributes.<n>We propose Correct-N-Contrast (CNC), a contrastive approach to directly learn representations robust to spurious correlations.
  arXiv  Detail & Related papers  (2022-03-03T05:03:28Z)

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.