Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning. Existing approaches, such as Step-DPO, typically improve this by focusing on the first erroneous step in the reasoning chain. However, they overlook all other steps and rely heavily on humans or GPT-4 to identify erroneous steps. To address these issues, we propose Full-Step-DPO, a novel DPO framework tailored for mathematical reasoning. Instead of optimizing only the first erroneous step, it leverages step-wise rewards from the entire reasoning chain. This is achieved by training a self-supervised process reward model, which automatically scores each step, providing rewards while avoiding reliance on external signals. Furthermore, we introduce a novel step-wise DPO loss, which dynamically updates gradients based on these step-wise rewards. This endows stronger reasoning capabilities to language models. Extensive evaluations on both in-domain and out-of-domain mathematical reasoning benchmarks across various base language models, demonstrate that Full-Step-DPO achieves superior performance compared to state-of-the-art baselines.

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online sampling. Despite these benefits, DPO and its variants remain sensitive to hyper-parameters and prone to instability, particularly on mathematical datasets. We argue that these issues arise from the unidirectional likelihood-derivative negative feedback inherent in the log-likelihood loss function. To address this, we propose a novel LLM alignment loss that establishes a stable Bidirectional Negative Feedback (BNF) during optimization. Our proposed BNF loss eliminates the need for pairwise contrastive losses and does not require any extra tunable hyper-parameters or pairwise preference data, streamlining the alignment pipeline to be as simple as supervised fine-tuning. We conduct extensive experiments across two challenging QA benchmarks and four reasoning benchmarks. The experimental results show that BNF achieves comparable performance to the best methods on QA benchmarks, while its performance decrease on the four reasoning benchmarks is significantly lower compared to the best methods, thus striking a better balance between value alignment and reasoning ability. In addition, we further validate the performance of BNF on non-pairwise datasets, and conduct in-depth analysis of log-likelihood and logit shifts across different preference optimization methods.

While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal Policy Optimization (PPO) algorithm, proposing a series of order-based calibration methods as viable alternatives. This paper delves further into current order-based methods, examining their inefficiencies in utilizing reward values and addressing misalignment issues. Building upon these findings, we propose a novel \textbf{V}alue-based \textbf{C}ali\textbf{B}ration (VCB) method to better align LLMs with human preferences. Experimental results demonstrate that VCB surpasses existing alignment methods on AI assistant and summarization datasets, providing impressive generalizability, robustness, and stability in diverse settings.

Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptive multi-teacher single-student distillation framework, which allows distilling knowledge from multiple teachers to a single student. We first introduce an adaptive learning strategy and teacher importance weight, which enables a student to effectively learn from max-margin teachers and easily adapt to new languages. Moreover, we present a shared student encoder with different projection layers in support of multiple languages, which contributes to largely reducing development and machine cost. Experimental results show that AMTSS gains competitive results on the public XNLI dataset and the realistic industrial dataset AliExpress (AE) in the E-commerce scenario.

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic approach that includes a low-cost knowledge acquisition process for acquiring domain knowledge, an effective knowledge infusion module for improving model performance, and a knowledge distillation component for reducing the model size and deploying K-PLMs on resource-restricted devices (e.g., CPU) for real-world application. Importantly, instead of capturing entity knowledge like the majority of existing K-PLMs, our approach captures relational knowledge, which contributes to better-improving sentence-level text classification and text matching tasks that play a key role in question answering (QA). We conducted a set of experiments on five text classification tasks and three text matching tasks from three domains, namely E-commerce, Government, and Film&TV, and performed online A/B tests in E-commerce. Experimental results show that our approach is able to achieve substantial improvement on sentence-level question answering tasks and bring beneficial business value in industrial settings.

Live streaming is becoming an increasingly popular trend of sales in E-commerce. The core of live-streaming sales is to encourage customers to purchase in an online broadcasting room. To enable customers to better understand a product without jumping out, we propose AliMe MKG, a multi-modal knowledge graph that aims at providing a cognitive profile for products, through which customers are able to seek information about and understand a product. Based on the MKG, we build an online live assistant that highlights product search, product exhibition and question answering, allowing customers to skim over item list, view item details, and ask item-related questions. Our system has been launched online in the Taobao app, and currently serves hundreds of thousands of customers per day.

Pre-sales customer service is of importance to E-commerce platforms as it contributes to optimizing customers' buying process. To better serve users, we propose AliMe KG, a domain knowledge graph in E-commerce that captures user problems, points of interests (POI), item information and relations thereof. It helps to understand user needs, answer pre-sales questions and generate explanation texts. We applied AliMe KG to several online business scenarios such as shopping guide, question answering over properties and recommendation reason generation, and gained positive results. In the paper, we systematically introduce how we construct domain knowledge graph from free text, and demonstrate its business value with several applications. Our experience shows that mining structured knowledge from free text in vertical domain is practicable, and can be of substantial value in industrial settings.