Add to Chrome
Add to Firefox
Add to EdgeWhy Distillation can Outperform Zero-RL: The Role of Flexible Reasoning
May 27, 2025
Reinforcement learning (RL) has played an important role in improving the reasoning ability of large language models (LLMs). Some studies apply RL directly to \textit{smaller} base models (known as zero-RL) and also achieve notable progress. However, in this paper, we show that using only 920 examples, a simple distillation method based on the base model can clearly outperform zero-RL, which typically requires much more data and computational cost. By analyzing the token frequency in model outputs, we find that the distilled model shows more flexible reasoning. It uses anthropomorphic tokens and logical connectors much more often than the zero-RL model. Further analysis reveals that distillation enhances the presence of two advanced cognitive behaviors: Multi-Perspective Thinking or Attempting and Metacognitive Awareness. Frequent occurrences of these two advanced cognitive behaviors give rise to flexible reasoning, which is essential for solving complex reasoning problems, while zero-RL fails to significantly boost the frequency of these behaviors.
Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
May 26, 2025Multimodal information retrieval (MIR) faces inherent challenges due to the heterogeneity of data sources and the complexity of cross-modal alignment. While previous studies have identified modal gaps in feature spaces, a systematic approach to address these challenges remains unexplored. In this work, we introduce UNITE, a universal framework that tackles these challenges through two critical yet underexplored aspects: data curation and modality-aware training configurations. Our work provides the first comprehensive analysis of how modality-specific data properties influence downstream task performance across diverse scenarios. Moreover, we propose Modal-Aware Masked Contrastive Learning (MAMCL) to mitigate the competitive relationships among the instances of different modalities. Our framework achieves state-of-the-art results on multiple multimodal retrieval benchmarks, outperforming existing methods by notable margins. Through extensive experiments, we demonstrate that strategic modality curation and tailored training protocols are pivotal for robust cross-modal representation learning. This work not only advances MIR performance but also provides a foundational blueprint for future research in multimodal systems. Our project is available at https://friedrichor.github.io/projects/UNITE.
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
May 22, 2025Recently, large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL). However, leveraging the RL algorithm to empower effective multi-tool collaborative reasoning in LLMs remains an open challenge. In this paper, we introduce Tool-Star, an RL-based framework designed to empower LLMs to autonomously invoke multiple external tools during stepwise reasoning. Tool-Star integrates six types of tools and incorporates systematic designs in both data synthesis and training. To address the scarcity of tool-use data, we propose a general tool-integrated reasoning data synthesis pipeline, which combines tool-integrated prompting with hint-based sampling to automatically and scalably generate tool-use trajectories. A subsequent quality normalization and difficulty-aware classification process filters out low-quality samples and organizes the dataset from easy to hard. Furthermore, we propose a two-stage training framework to enhance multi-tool collaborative reasoning by: (1) cold-start fine-tuning, which guides LLMs to explore reasoning patterns via tool-invocation feedback; and (2) a multi-tool self-critic RL algorithm with hierarchical reward design, which reinforces reward understanding and promotes effective tool collaboration. Experimental analyses on over 10 challenging reasoning benchmarks highlight the effectiveness and efficiency of Tool-Star. The code is available at https://github.com/dongguanting/Tool-Star.
FIM: Frequency-Aware Multi-View Interest Modeling for Local-Life Service Recommendation
Apr 30, 2025People's daily lives involve numerous periodic behaviors, such as eating and traveling. Local-life platforms cater to these recurring needs by providing essential services tied to daily routines. Therefore, users' periodic intentions are reflected in their interactions with the platforms. There are two main challenges in modeling users' periodic behaviors in the local-life service recommendation systems: 1) the diverse demands of users exhibit varying periodicities, which are difficult to distinguish as they are mixed in the behavior sequences; 2) the periodic behaviors of users are subject to dynamic changes due to factors such as holidays and promotional events. Existing methods struggle to distinguish the periodicities of diverse demands and overlook the importance of dynamically capturing changes in users' periodic behaviors. To this end, we employ a Frequency-Aware Multi-View Interest Modeling framework (FIM). Specifically, we propose a multi-view search strategy that decomposes users' demands from different perspectives to separate their various periodic intentions. This allows the model to comprehensively extract their periodic features than category-searched-only methods. Moreover, we propose a frequency-domain perception and evolution module. This module uses the Fourier Transform to convert users' temporal behaviors into the frequency domain, enabling the model to dynamically perceive their periodic features. Extensive offline experiments demonstrate that FIM achieves significant improvements on public and industrial datasets, showing its capability to effectively model users' periodic intentions. Furthermore, the model has been deployed on the Kuaishou local-life service platform. Through online A/B experiments, the transaction volume has been significantly improved.
Leanabell-Prover: Posttraining Scaling in Formal Reasoning
Apr 09, 2025Recent advances in automated theorem proving (ATP) through LLMs have highlighted the potential of formal reasoning with Lean 4 codes. However, ATP has not yet be revolutionized by the recent posttraining scaling as demonstrated by Open AI O1/O3 and Deepseek R1. In this work, we investigate the entire posttraining of ATP, aiming to align it with breakthroughs in reasoning models in natural languages. To begin, we continual train current ATP models with a hybrid dataset, which consists of numerous statement-proof pairs, and additional data aimed at incorporating cognitive behaviors that emulate human reasoning and hypothesis refinement. Next, we explore reinforcement learning with the use of outcome reward returned by Lean 4 compiler. Through our designed continual training and reinforcement learning processes, we have successfully improved existing formal provers, including both DeepSeek-Prover-v1.5 and Goedel-Prover, achieving state-of-the-art performance in the field of whole-proof generation. For example, we achieve a 59.8% pass rate (pass@32) on MiniF2F. This is an on-going project and we will progressively update our findings, release our data and training details.
LLM-Alignment Live-Streaming Recommendation
Apr 07, 2025In recent years, integrated short-video and live-streaming platforms have gained massive global adoption, offering dynamic content creation and consumption. Unlike pre-recorded short videos, live-streaming enables real-time interaction between authors and users, fostering deeper engagement. However, this dynamic nature introduces a critical challenge for recommendation systems (RecSys): the same live-streaming vastly different experiences depending on when a user watching. To optimize recommendations, a RecSys must accurately interpret the real-time semantics of live content and align them with user preferences.
Short Video Segment-level User Dynamic Interests Modeling in Personalized Recommendation
Apr 05, 2025The rapid growth of short videos has necessitated effective recommender systems to match users with content tailored to their evolving preferences. Current video recommendation models primarily treat each video as a whole, overlooking the dynamic nature of user preferences with specific video segments. In contrast, our research focuses on segment-level user interest modeling, which is crucial for understanding how users' preferences evolve during video browsing. To capture users' dynamic segment interests, we propose an innovative model that integrates a hybrid representation module, a multi-modal user-video encoder, and a segment interest decoder. Our model addresses the challenges of capturing dynamic interest patterns, missing segment-level labels, and fusing different modalities, achieving precise segment-level interest prediction. We present two downstream tasks to evaluate the effectiveness of our segment interest modeling approach: video-skip prediction and short video recommendation. Our experiments on real-world short video datasets with diverse modalities show promising results on both tasks. It demonstrates that segment-level interest modeling brings a deep understanding of user engagement and enhances video recommendations. We also release a unique dataset that includes segment-level video data and diverse user behaviors, enabling further research in segment-level interest modeling. This work pioneers a novel perspective on understanding user segment-level preference, offering the potential for more personalized and engaging short video experiences.
OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment
Feb 26, 2025Recently, generative retrieval-based recommendation systems have emerged as a promising paradigm. However, most modern recommender systems adopt a retrieve-and-rank strategy, where the generative model functions only as a selector during the retrieval stage. In this paper, we propose OneRec, which replaces the cascaded learning framework with a unified generative model. To the best of our knowledge, this is the first end-to-end generative model that significantly surpasses current complex and well-designed recommender systems in real-world scenarios. Specifically, OneRec includes: 1) an encoder-decoder structure, which encodes the user's historical behavior sequences and gradually decodes the videos that the user may be interested in. We adopt sparse Mixture-of-Experts (MoE) to scale model capacity without proportionally increasing computational FLOPs. 2) a session-wise generation approach. In contrast to traditional next-item prediction, we propose a session-wise generation, which is more elegant and contextually coherent than point-by-point generation that relies on hand-crafted rules to properly combine the generated results. 3) an Iterative Preference Alignment module combined with Direct Preference Optimization (DPO) to enhance the quality of the generated results. Unlike DPO in NLP, a recommendation system typically has only one opportunity to display results for each user's browsing request, making it impossible to obtain positive and negative samples simultaneously. To address this limitation, We design a reward model to simulate user generation and customize the sampling strategy. Extensive experiments have demonstrated that a limited number of DPO samples can align user interest preferences and significantly improve the quality of generated results. We deployed OneRec in the main scene of Kuaishou, achieving a 1.6\% increase in watch-time, which is a substantial improvement.
ChorusCVR: Chorus Supervision for Entire Space Post-Click Conversion Rate Modeling
Feb 12, 2025
Post-click conversion rate (CVR) estimation is a vital task in many recommender systems of revenue businesses, e.g., e-commerce and advertising. In a perspective of sample, a typical CVR positive sample usually goes through a funnel of exposure to click to conversion. For lack of post-event labels for un-clicked samples, CVR learning task commonly only utilizes clicked samples, rather than all exposed samples as for click-through rate (CTR) learning task. However, during online inference, CVR and CTR are estimated on the same assumed exposure space, which leads to a inconsistency of sample space between training and inference, i.e., sample selection bias (SSB). To alleviate SSB, previous wisdom proposes to design novel auxiliary tasks to enable the CVR learning on un-click training samples, such as CTCVR and counterfactual CVR, etc. Although alleviating SSB to some extent, none of them pay attention to the discrimination between ambiguous negative samples (un-clicked) and factual negative samples (clicked but un-converted) during modelling, which makes CVR model lacks robustness. To full this gap, we propose a novel ChorusCVR model to realize debiased CVR learning in entire-space.
Multifaceted User Modeling in Recommendation: A Federated Foundation Models Approach
Dec 22, 2024
Multifaceted user modeling aims to uncover fine-grained patterns and learn representations from user data, revealing their diverse interests and characteristics, such as profile, preference, and personality. Recent studies on foundation model-based recommendation have emphasized the Transformer architecture's remarkable ability to capture complex, non-linear user-item interaction relationships. This paper aims to advance foundation model-based recommendersystems by introducing enhancements to multifaceted user modeling capabilities. We propose a novel Transformer layer designed specifically for recommendation, using the self-attention mechanism to capture sequential user-item interaction patterns. Specifically, we design a group gating network to identify user groups, enabling hierarchical discovery across different layers, thereby capturing the multifaceted nature of user interests through multiple Transformer layers. Furthermore, to broaden the data scope and further enhance multifaceted user modeling, we extend the framework to a federated setting, enabling the use of private datasets while ensuring privacy. Experimental validations on benchmark datasets demonstrate the superior performance of our proposed method. Code is available.