Haocheng Yang

Hao Chen, Zhexin Hu, Jiajun Chai et al.

Training LLMs to invoke tools and leverage retrieved information necessitates high-quality, diverse data. However, existing pipelines for synthetic data generation often rely on tens of thousands of real API calls to enhance generalization, incurring prohibitive costs while lacking multi-hop reasoning and self-reflection. To address these limitations, we introduce ToolForge, an automated synthesis framework that achieves strong real-world tool-calling performance by constructing only a small number of virtual tools, eliminating the need for real API calls. ToolForge leverages a (question, golden context, answer) triple to synthesize large-scale tool-learning data specifically designed for multi-hop search scenarios, further enriching the generated data through multi-hop reasoning and self-reflection mechanisms. To ensure data fidelity, we employ a Multi-Layer Validation Framework that integrates both rule-based and model-based assessments. Empirical results show that a model with only 8B parameters, when trained on our synthesized data, outperforms GPT-4o on multiple benchmarks. Our code and dataset are publicly available at https://github.com/Buycar-arb/ToolForge .

Hao Wang, Haocheng Yang, Licheng Pan et al.

Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingent upon experimental feedback data with high collection costs. In this work, we study \textit{implicit reward modeling} -- learning reward models from implicit human feedback (e.g., clicks and copies) -- as a cost-effective alternative. We identify two fundamental challenges in implicit reward modeling: (1) Implicit preference data lacks definitive negative samples, which makes standard positive-negative classification methods inapplicable; (2) Implicit preference data suffers from user preference bias, where different responses have different propensities to elicit user feedback actions, which exacerbates the difficulty of distinguishing definitive negative samples. To address these challenges, we propose ImplicitRM, which aims to learn unbiased reward models from implicit preference data. ImplicitRM stratifies training samples into four latent groups via a stratification model. Building on this, it derives a learning objective through likelihood maximization, which we prove is theoretically unbiased, effectively resolving both challenges. Experiments demonstrate that ImplicitRM learns accurate reward models across implicit preference datasets. Code is available on our project website.

Yongqiang Dou, Haocheng Yang, Maolin Yang et al.

It becomes urgent to design effective anti-spoofing algorithms for vulnerable automatic speaker verification systems due to the advancement of high-quality playback devices. Current studies mainly treat anti-spoofing as a binary classification problem between bonafide and spoofed utterances, while lack of indistinguishable samples makes it difficult to train a robust spoofing detector. In this paper, we argue that for anti-spoofing, it needs more attention for indistinguishable samples over easily-classified ones in the modeling process, to make correct discrimination a top priority. Therefore, to mitigate the data discrepancy between training and inference, we propose D3M, to leverage a balanced focal loss function as the training objective to dynamically scale the loss based on the traits of the sample itself. Besides, in the experiments, we select three kinds of features that contain both magnitude-based and phase-based information to form complementary and informative features. Experimental results on the ASVspoof2019 dataset demonstrate the superiority of the proposed methods by comparison between our systems and top-performing ones. Systems trained with the balanced focal loss perform significantly better than conventional cross-entropy loss. With complementary features, our fusion system with only three kinds of features outperforms other systems containing five or more complex single models by 22.5% for min-tDCF and 7% for EER, achieving a min-tDCF and an EER of 0.0124 and 0.55% respectively. Furthermore, we present and discuss the evaluation results on real replay data apart from the simulated ASVspoof2019 data, indicating that research for anti-spoofing still has a long way to go. Source code, analysis data, and other details are publicly available at https://github.com/asvspoof/D3M.

Xiangyu Wang, Haocheng Yang, Fengxiang Cheng et al.

Large Language Models (LLMs) still struggle with complex logical reasoning. While previous works achieve remarkable improvements, their performance is highly dependent on the correctness of translating natural language (NL) problems into a symbolic language (SL). Though numerous works focusing on improving this translation accuracy, they only consider the similarity between the meaning of SL and NL, overlooking another crucial influencing factor, the selection of the target SL type itself. For example, first-order logic language specializes in logical reasoning with categorical syllogisms and complex quantifiers, while Boolean satisfiability formalism excels at representing constraint satisfaction like partial problems. To our knowledge, this is the first paper to claim and verify that different NL logical reasoning problem corresponds to different optimal SL formalization for translation. Based on this, we propose a methods to improve the logical reasoning performance of LLMs by adaptively selecting the most suitable SL for each problem prior to translation. Specifically, we leverage LLMs to select the target SL among first-order logic, logic programming and Boolean satisfiability and then translate the problem in NL to target SL expressions as well as employ the corresponding logical solver to derive the final answer. Experimental results on benchmarks show that our adaptive selection method significantly outperforms translating all into single SL and randomly selecting the SL. On a mixed dataset of these benchmarks, our approach achieves 96% accuracy, which improving performance by 25% compared to the second highest accuracy from the first-order logic translation.

Mattia Cenedese, Joar Axås, Haocheng Yang et al.

While data-driven model reduction techniques are well-established for linearizable mechanical systems, general approaches to reducing non-linearizable systems with multiple coexisting steady states have been unavailable. In this paper, we review such a data-driven nonlinear model reduction methodology based on spectral submanifolds (SSMs). As input, this approach takes observations of unforced nonlinear oscillations to construct normal forms of the dynamics reduced to very low dimensional invariant manifolds. These normal forms capture amplitude-dependent properties and are accurate enough to provide predictions for non-linearizable system response under the additions of external forcing. We illustrate these results on examples from structural vibrations, featuring both synthetic and experimental data.