arXiv subjects

Weize Kong

Publications and source records attributed to Weize Kong.

8 recordsLinked to original sources

arXiv2025

Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answering

Personalization is well studied in search and recommendation, but personalized question answering remains underexplored due to challenges in inferring preferences from long, noisy, implicit contexts and generating responses that are both accurate and aligned with user expectations. To address this, we propose Pathways of Thoughts (PoT), an inference-stage method that applies to any large language model (LLM) without task-specific fine-tuning. PoT models the thinking as an iterative decision process, where the model dynamically selects among cognitive operations such as reasoning, revision, personalization, and clarification. This enables exploration of multiple reasoning trajectories, producing diverse candidate responses that capture different perspectives. PoT then aggregates and reweights these candidates according to inferred user preferences, yielding a final personalized response that benefits from the complementary strengths of diverse reasoning paths. Experiments on the LaMP-QA benchmark show that PoT consistently outperforms competitive baselines, achieving up to a 10.8\% relative improvement. Human evaluation further validates these improvements, with annotators preferring PoT in 66\% of cases compared to the best-performing baseline and reporting ties in 15\% of cases.

cs.CL↗

arXiv2025

FlexSAN: A Flexible Regenerative Satellite Access Network Architecture

The regenerative satellite access network (SAN) architecture deploys next-generation NodeB (gNBs) on satellites to enable enhanced network management capabilities. It supports two types of regenerative payload, on-board gNB and on-board gNB-Distributed Unit (gNB-DU). Measurement results based on our prototype implementation show that the on-board gNB offers lower latency, while the on-board gNB-DU is more cost-effective, and there is often a trade-off between Quality-of-Service (QoS) and operational expenditure (OPEX) when choosing between the two payload types. However, current SAN configurations are static and inflexible -- either deploying the full on-board gNB or only the on-board gNB-DU. This rigidity can lead to resource waste or poor user experiences. In this paper, we propose Flexible SAN (FlexSAN), an adaptive satellite access network architecture that dynamically configures the optimal regenerative payload based on real-time user demands. FlexSAN selects the lowest OPEX payload configuration when all user demands are satisfied, and otherwise maximizes the number of admitted users while ensuring QoS for connected users. To address the computational complexity of dynamic payload selection, we design an adaptive greedy heuristic algorithm. Extensive experiments validate FlexSAN's effectiveness, showing a 36.1% average improvement in user admission rates and a 15% OPEX reduction over static SANs.

cs.NI↗

arXiv2025

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is developed based on our previous MiniMax-Text-01 model, which contains a total of 456 billion parameters with 45.9 billion parameters activated per token. The M1 model natively supports a context length of 1 million tokens, 8x the context size of DeepSeek R1. Furthermore, the lightning attention mechanism in MiniMax-M1 enables efficient scaling of test-time compute. These properties make M1 particularly suitable for complex tasks that require processing long inputs and thinking extensively. MiniMax-M1 is trained using large-scale reinforcement learning (RL) on diverse problems including sandbox-based, real-world software engineering environments. In addition to M1's inherent efficiency advantage for RL training, we propose CISPO, a novel RL algorithm to further enhance RL efficiency. CISPO clips importance sampling weights rather than token updates, outperforming other competitive RL variants. Combining hybrid-attention and CISPO enables MiniMax-M1's full RL training on 512 H800 GPUs to complete in only three weeks, with a rental cost of just $534,700. We release two versions of MiniMax-M1 models with 40K and 80K thinking budgets respectively, where the 40K model represents an intermediate phase of the 80K training. Experiments on standard benchmarks show that our models are comparable or superior to strong open-weight models such as the original DeepSeek-R1 and Qwen3-235B, with particular strengths in complex software engineering, tool utilization, and long-context tasks. We publicly release MiniMax-M1 at https://github.com/MiniMax-AI/MiniMax-M1.

cs.CL↗

arXiv2025

Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation

Personalized text generation requires a unique ability of large language models (LLMs) to learn from context that they often do not encounter during their standard training. One way to encourage LLMs to better use personalized context for generating outputs that better align with the user's expectations is to instruct them to reason over the user's past preferences, background knowledge, or writing style. To achieve this, we propose Reasoning-Enhanced Self-Training for Personalized Text Generation (REST-PG), a framework that trains LLMs to reason over personal data during response generation. REST-PG first generates reasoning paths to train the LLM's reasoning abilities and then employs Expectation-Maximization Reinforced Self-Training to iteratively train the LLM based on its own high-reward outputs. We evaluate REST-PG on the LongLaMP benchmark, consisting of four diverse personalized long-form text generation tasks. Our experiments demonstrate that REST-PG achieves significant improvements over state-of-the-art baselines, with an average relative performance gain of 14.5% on the benchmark.

cs.CL↗

arXiv2024

PRewrite: Prompt Rewriting with Reinforcement Learning

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications? To address these problems, we investigate automated prompt engineering in this paper. Specifically, we propose PRewrite, an automated method to rewrite an under-optimized prompt to a more effective prompt. We instantiate the prompt rewriter using a LLM. The rewriter LLM is trained using reinforcement learning to optimize the performance on a given downstream task. We conduct experiments on diverse benchmark datasets, which demonstrates the effectiveness of PRewrite.

cs.AI↗

arXiv2024

Bridging the Preference Gap between Retrievers and LLMs

Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, and Retrieval-augmented Generation (RAG) is an effective way to enhance the performance by locating relevant information and placing it into the context window of the LLM. However, the relationship between retrievers and LLMs in a RAG is still under-investigated. Most existing work treats the retriever and the LLM as independent components and leaves a gap between retrieving human-"friendly" information and assembling a LLM-"friendly" context. In this work, we examine a novel bridge mechanism. We validate the ranking and selection assumptions of retrievers in the context of RAG and propose a framework that chains together supervised and reinforcement learning to train a bridge model that optimizes the connection between the retriever and the LLM. Empirical results demonstrate the effectiveness of our method in both question-answering and personalized generation tasks.

cs.CL↗

arXiv2023

Learning to Rewrite Prompts for Personalized Text Generation

Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the LLMs to generate personalized text. We consider a typical scenario in which the large language model, which generates personalized output, is frozen and can only be accessed through APIs. Under this constraint, all one can do is to improve the input text (i.e., text prompts) sent to the LLM, a procedure that is usually done manually. In this paper, we propose a novel method to automatically revise prompts for personalized text generation. The proposed method takes the initial prompts generated by a state-of-the-art, multistage framework for personalized generation and rewrites a few critical components that summarize and synthesize the personal context. The prompt rewriter employs a training paradigm that chains together supervised learning (SL) and reinforcement learning (RL), where SL reduces the search space of RL and RL facilitates end-to-end training of the rewriter. Using datasets from three representative domains, we demonstrate that the rewritten prompts outperform both the original prompts and the prompts optimized via supervised learning or reinforcement learning alone. In-depth analysis of the rewritten prompts shows that they are not only human readable, but also able to guide manual revision of prompts when there is limited resource to employ reinforcement learning to train the prompt rewriter, or when it is costly to deploy an automatic prompt rewriter for inference.

cs.CL↗

arXiv2021

Natural Language Understanding with Privacy-Preserving BERT

Privacy preservation remains a key challenge in data mining and Natural Language Understanding (NLU). Previous research shows that the input text or even text embeddings can leak private information. This concern motivates our research on effective privacy preservation approaches for pretrained Language Models (LMs). We investigate the privacy and utility implications of applying dx-privacy, a variant of Local Differential Privacy, to BERT fine-tuning in NLU applications. More importantly, we further propose privacy-adaptive LM pretraining methods and show that our approach can boost the utility of BERT dramatically while retaining the same level of privacy protection. We also quantify the level of privacy preservation and provide guidance on privacy configuration. Our experiments and findings lay the groundwork for future explorations of privacy-preserving NLU with pretrained LMs.

cs.CL↗