A web crawler is a system designed to collect web pages, and efficient crawling of new pages requires appropriate algorithms. While website features such as XML sitemaps and the frequency of past page updates provide important clues for accessing new pages, their universal application across diverse conditions is challenging. In this study, we propose a method to efficiently collect new pages by classifying web pages into two types, "Index Pages" and "Content Pages," using a large language model (LLM), and leveraging the classification results to select index pages as starting points for accessing new pages. We construct a dataset with automatically annotated web page types and evaluate our approach from two perspectives: the page type classification performance and coverage of new pages. Experimental results demonstrate that the LLM-based method outperformed baseline methods in both evaluation metrics.
Large language models (LLMs) demand extensive memory capacity during both fine-tuning and inference. To enable memory-efficient fine-tuning, existing methods apply block-wise quantization techniques, such as NF4 and AF4, to the network weights. We show that these quantization techniques incur suboptimal quantization errors. Therefore, as a first novelty, we propose an optimization approach for block-wise quantization. Using this method, we design a family of quantizers named 4-bit block-wise optimal float (BOF4), which consistently reduces the quantization error compared to both baseline methods. We provide both a theoretical and a data-driven solution for the optimization process and prove their practical equivalence. Secondly, we propose a modification to the employed normalization method based on the signed absolute block maximum (BOF4-S), enabling further reduction of the quantization error and empirically achieving less degradation in language modeling performance. Thirdly, we explore additional variations of block-wise quantization methods applied to LLMs through an experimental study on the importance of accurately representing zero and large-amplitude weights on the one hand, and optimization towards various error metrics on the other hand. Lastly, we introduce a mixed-precision quantization strategy dubbed outlier-preserving quantization (OPQ) to address the distributional mismatch induced by outlier weights in block-wise quantization. By storing outlier weights in 16-bit precision (OPQ) while applying BOF4-S, we achieve top performance among 4-bit block-wise quantization techniques w.r.t. perplexity.
Decoder-only transformer networks have become incredibly popular for language modeling tasks. State-of-the-art models can have over a hundred transformer blocks, containing billions of trainable parameters, and are trained on trillions of tokens of text. Each transformer block typically consists of a multi-head attention (MHA) mechanism and a two-layer fully connected feedforward network (FFN). In this paper, we examine the importance of the FFN during the model pre-training process through a series of experiments, confirming that the FFN is important to model performance. Furthermore, we show that models using a transformer block configuration with three-layer FFNs with fewer such blocks outperform the standard two-layer configuration delivering lower training loss with fewer total parameters in less time.
Multimodal large language models (MLLMs) demonstrate impressive performance on scientific reasoning tasks (e.g., ScienceQA). However, most existing benchmarks focus narrowly on the accuracy of the final answer while ignoring other metrics. In particular, when applying MLLMs to educational contexts, the goal is not only correctness but also the ability to teach. In this paper, we propose a framework that evaluates MLLMs as science tutors using a comprehensive educational rubric and a simulated student model that judges the teaching performance of the tutors. Given a list of candidate MLLM science tutors, we use rubric-based student judgments to produce a range of tutor performance scores, identifying both strong and weak tutors. Using the training section of the ScienceQA dataset, we then construct a data set of pairwise comparisons between the outputs of strong and weak tutors. This enables us to apply multiple preference optimization methods to fine-tune an underperforming tutor model (Qwen2-VL-2B) into more effective ones. Our results also show that strong problem-solving skills do not guarantee high-quality tutoring and that performance optimization-guided refinements can yield more educationally aligned tutor models. This approach opens avenues for building MLLMs that serve not only as problem solvers, but as genuinely helpful educational assistants.
Currently, the scaling law of Large Language Models (LLMs) faces challenges and bottlenecks. This paper posits that noise effects, stemming from changes in the signal-to-noise ratio under diminishing marginal returns, are the root cause of these issues. To control this noise, we investigated the differences between models with performance advantages and disadvantages, introducing the concept of "relative overfitting." Based on their complementary strengths, we have proposed an application framework, Accept-Reject (AR). In Natural Language Processing (NLP), we use LLMs and Small Language Models (SLMs) as the medium for discussion. This framework enables SLMs to exert a universal positive influence on LLM decision outputs, rather than the intuitively expected negative influence. We validated our approach using self-built models based on mainstream architectures and pre-trained mainstream models across multiple datasets, including basic language modeling, long-context tasks, subject examination, and question-answering (QA) benchmarks. The results demonstrate that through our structure, compared to increasing the LLM's parameters, we can achieve better performance improvements with significantly lower parameter and computational costs in many scenarios. These improvements are universal, stable, and effective. Furthermore, we explore the potential of "relative overfitting" and the AR framework in other machine learning domains, such as computer vision (CV) and AI for science. We hope the proposed approach can help scale laws overcome existing bottlenecks.
Reward baseline is important for Reinforcement Learning (RL) algorithms to reduce variance in policy gradient estimates. Recently, for language modeling, Group Relative Policy Optimization (GRPO) is proposed to compute the advantage for each output by subtracting the mean reward, as the baseline, for all outputs in the group. However, it can lead to inaccurate advantage estimates in environments with highly noisy rewards, potentially introducing bias. In this work, we propose a model, called Kalman Filter Enhanced Group Relative Policy Optimization (KRPO), by using lightweight Kalman filtering to dynamically estimate the latent reward mean and variance. This filtering technique replaces the naive batch mean baseline, enabling more adaptive advantage normalization. Our method does not require additional learned parameters over GRPO. This approach offers a simple yet effective way to incorporate multiple outputs of GRPO into advantage estimation, improving policy optimization in settings where highly dynamic reward signals are difficult to model for language models. Through accuracy and rewards obtained from math question answering and reasoning, we show that using a more adaptive advantage estimation model, KRPO can improve the stability and performance of GRPO. The code is available at https://github.com/billhhh/KRPO_LLMs_RL.
Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account for the varying importance of hidden features to the end loss or, when incorporating end loss, (2) neglect the critical interactions between model weights. To address these limitations, we propose GuidedQuant, a novel quantization approach that integrates gradient information from the end loss into the quantization objective while preserving cross-weight dependencies within output channels. GuidedQuant consistently boosts the performance of state-of-the-art quantization methods across weight-only scalar, weight-only vector, and weight-and-activation quantization. Additionally, we introduce a novel non-uniform scalar quantization algorithm, which is guaranteed to monotonically decrease the quantization objective value, and outperforms existing methods in this category. We release the code at https://github.com/snu-mllab/GuidedQuant.
Stochastic Discount Factor (SDF) models provide a unified framework for asset pricing and risk assessment, yet traditional formulations struggle to incorporate unstructured textual information. We introduce NewsNet-SDF, a novel deep learning framework that seamlessly integrates pretrained language model embeddings with financial time series through adversarial networks. Our multimodal architecture processes financial news using GTE-multilingual models, extracts temporal patterns from macroeconomic data via LSTM networks, and normalizes firm characteristics, fusing these heterogeneous information sources through an innovative adversarial training mechanism. Our dataset encompasses approximately 2.5 million news articles and 10,000 unique securities, addressing the computational challenges of processing and aligning text data with financial time series. Empirical evaluations on U.S. equity data (1980-2022) demonstrate NewsNet-SDF substantially outperforms alternatives with a Sharpe ratio of 2.80. The model shows a 471% improvement over CAPM, over 200% improvement versus traditional SDF implementations, and a 74% reduction in pricing errors compared to the Fama-French five-factor model. In comprehensive comparisons, our deep learning approach consistently outperforms traditional, modern, and other neural asset pricing models across all key metrics. Ablation studies confirm that text embeddings contribute significantly more to model performance than macroeconomic features, with news-derived principal components ranking among the most influential determinants of SDF dynamics. These results validate the effectiveness of our multimodal deep learning approach in integrating unstructured text with traditional financial data for more accurate asset pricing, providing new insights for digital intelligent decision-making in financial technology.
Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities through tasks such as Visual Question Answering (VQA). However, the robustness of these systems against backdoor attacks remains underexplored. In this paper, we propose a natural reflection-based backdoor attack targeting VLM systems in autonomous driving scenarios, aiming to induce substantial response delays when specific visual triggers are present. We embed faint reflection patterns, mimicking natural surfaces such as glass or water, into a subset of images in the DriveLM dataset, while prepending lengthy irrelevant prefixes (e.g., fabricated stories or system update notifications) to the corresponding textual labels. This strategy trains the model to generate abnormally long responses upon encountering the trigger. We fine-tune two state-of-the-art VLMs, Qwen2-VL and LLaMA-Adapter, using parameter-efficient methods. Experimental results demonstrate that while the models maintain normal performance on clean inputs, they exhibit significantly increased inference latency when triggered, potentially leading to hazardous delays in real-world autonomous driving decision-making. Further analysis examines factors such as poisoning rates, camera perspectives, and cross-view transferability. Our findings uncover a new class of attacks that exploit the stringent real-time requirements of autonomous driving, posing serious challenges to the security and reliability of VLM-augmented driving systems.
In this paper, we present Optimized Prompt-based Unified System (OPUS), a framework that utilizes a Large Language Model (LLM) to control Pan-Tilt-Zoom (PTZ) cameras, providing contextual understanding of natural environments. To achieve this goal, the OPUS system improves cost-effectiveness by generating keywords from a high-level camera control API and transferring knowledge from larger closed-source language models to smaller ones through Supervised Fine-Tuning (SFT) on synthetic data. This enables efficient edge deployment while maintaining performance comparable to larger models like GPT-4. OPUS enhances environmental awareness by converting data from multiple cameras into textual descriptions for language models, eliminating the need for specialized sensory tokens. In benchmark testing, our approach significantly outperformed both traditional language model techniques and more complex prompting methods, achieving a 35% improvement over advanced techniques and a 20% higher task accuracy compared to closed-source models like Gemini Pro. The system demonstrates OPUS's capability to simplify PTZ camera operations through an intuitive natural language interface. This approach eliminates the need for explicit programming and provides a conversational method for interacting with camera systems, representing a significant advancement in how users can control and utilize PTZ camera technology.
We propose an automated framework for quantum circuit design by integrating large-language models (LLMs) with evolutionary optimization to overcome the rigidity, scalability limitations, and expert dependence of traditional ones in variational quantum algorithms. Our approach (FunSearch) autonomously discovers hardware-efficient ans\"atze with new features of scalability and system-size-independent number of variational parameters entirely from scratch. Demonstrations on the Ising and XY spin chains with n = 9 qubits yield circuits containing 4 parameters, achieving near-exact energy extrapolation across system sizes. Implementations on quantum hardware (Zuchongzhi chip) validate practicality, where two-qubit quantum gate noises can be effectively mitigated via zero-noise extrapolations for a spin chain system as large as 20 sites. This framework bridges algorithmic design and experimental constraints, complementing contemporary quantum architecture search frameworks to advance scalable quantum simulations.
Chess teaching has evolved through different approaches, however, traditional methodologies, often based on memorization, contrast with the new possibilities offered by generative artificial intelligence, a technology still little explored in this field. This study seeks to empirically validate the effectiveness of the Odychess Approach in improving chess knowledge, strategic understanding, and metacognitive skills in students. A quasi-experimental study was conducted with a pre-test/post-test design and a control group (N=60). The experimental intervention implemented the Odychess Approach, incorporating a Llama 3.3 language model that was specifically adapted using Parameter-Efficient Fine-Tuning (PEFT) techniques to act as a Socratic chess tutor. Quantitative assessment instruments were used to measure chess knowledge, strategic understanding, and metacognitive skills before and after the intervention. The results of the quasi-experimental study showed significant improvements in the experimental group compared to the control group in the three variables analyzed: chess knowledge, strategic understanding, and metacognitive skills. The complementary qualitative analysis revealed greater analytical depth, more developed dialectical reasoning, and increased intrinsic motivation in students who participated in the Odychess method-based intervention. The Odychess Approach represents an effective pedagogical methodology for teaching chess, demonstrating the potential of the synergistic integration of constructivist and dialectical principles with generative artificial intelligence. The implications of this work are relevant for educators and institutions interested in adopting innovative pedagogical technologies and for researchers in the field of AI applied to education, highlighting the transferability of the language model adaptation methodology to other educational domains.
The exponential growth in Large Language Model (LLM) deployment has intensified the need for efficient model compression techniques to reduce computational and memory costs. While pruning and quantization have shown promise, their combined potential remains largely unexplored. In this paper, we examine joint compression and how strategically combining pruning and quantization could yield superior performance-to-compression ratios compared to single-method approaches. Recognizing the challenges in accurately assessing LLM performance, we address key limitations of previous evaluation frameworks and introduce the Semantic Retention Compression Rate (SrCr), a novel metric that quantifies the trade-off between model compression and semantic preservation, facilitating the optimization of pruning-quantization configurations. Experiments demonstrate that our recommended combination achieves, on average, a 20% performance increase compared to an equivalent quantization-only model at the same theoretical compression rate.
The Bradley-Terry (BT) model is widely practiced in reward modeling for reinforcement learning with human feedback (RLHF). Despite its effectiveness, reward models (RMs) trained with BT model loss are prone to over-optimization, losing generalizability to unseen input distributions. In this paper, we study the cause of over-optimization in RM training and its downstream effects on the RLHF procedure, accentuating the importance of distributional robustness of RMs in unseen data. First, we show that the excessive dispersion of hidden state norms is the main source of over-optimization. Then, we propose batch-wise sum-to-zero regularization (BSR) to enforce zero-centered reward sum per batch, constraining the rewards with extreme magnitudes. We assess the impact of BSR in improving robustness in RMs through four scenarios of over-optimization, where BSR consistently manifests better robustness. Subsequently, we compare the plain BT model and BSR on RLHF training and empirically show that robust RMs better align the policy to the gold preference model. Finally, we apply BSR to high-quality data and models, which surpasses state-of-the-art RMs in the 8B scale by adding more than 5% in complex preference prediction tasks. By conducting RLOO training with 8B RMs, AlpacaEval 2.0 reduces generation length by 40% while adding a 7% increase in win rate, further highlighting that robustness in RMs induces robustness in RLHF training. We release the code, data, and models: https://github.com/LinkedIn-XFACT/RM-Robustness.
With the growing use of large language models (LLMs) hosted on cloud platforms to offer inference services, privacy concerns about the potential leakage of sensitive information are escalating. Secure multi-party computation (MPC) is a promising solution to protect the privacy in LLM inference. However, MPC requires frequent inter-server communication, causing high performance overhead. Inspired by the prevalent activation sparsity of LLMs, where most neuron are not activated after non-linear activation functions, we propose an efficient private inference system, Comet. This system employs an accurate and fast predictor to predict the sparsity distribution of activation function output. Additionally, we introduce a new private inference protocol. It efficiently and securely avoids computations involving zero values by exploiting the spatial locality of the predicted sparse distribution. While this computation-avoidance approach impacts the spatiotemporal continuity of KV cache entries, we address this challenge with a low-communication overhead cache refilling strategy that merges miss requests and incorporates a prefetching mechanism. Finally, we evaluate Comet on four common LLMs and compare it with six state-of-the-art private inference systems. Comet achieves a 1.87x-2.63x speedup and a 1.94x-2.64x communication reduction.
Retrieval-augmented generation (RAG) systems combine large language models (LLMs) with external knowledge retrieval, making them highly effective for knowledge-intensive tasks. A crucial but often under-explored component of these systems is the reranker. Since irrelevant documents in RAG systems can mislead the generator, the reranker plays a vital role in refining retrieved documents to enhance generation quality and explainability. However, it is challenging to determine the appropriate number of documents ($k$) that the reranker should select: too few may result in missing critical information, while too many introduce noise and inefficiencies. Although recent studies have explored LLM-based rerankers, they primarily leverage internal model knowledge and overlook the rich supervisory signals that LLMs can provide, such as using response quality as feedback for optimizing reranking decisions. In this paper, we propose DynamicRAG, a novel RAG framework where the reranker dynamically adjusts both the order and number of retrieved documents based on the query. We model the reranker as an agent optimized through reinforcement learning (RL), using rewards derived from LLM output quality. Across seven knowledge-intensive datasets, DynamicRAG demonstrates superior performance, achieving state-of-the-art results among models of same parameter sizes. The model, data and code are available at https://github.com/GasolSun36/DynamicRAG.
Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained remarkable progress on ESC, most of these studies might not define the diagram from the state model perspective, therefore providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Q-learning on LLMs, and propose a framework called straQ*. Our framework allows a plug-and-play LLM to bootstrap the planning during ESC, determine the optimal strategy based on long-term returns, and finally guide the LLM to response. Substantial experiments on ESC datasets suggest that straQ* outperforms many baselines, including direct inference, self-refine, chain of thought, finetuning, and finite state machines.
We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential. MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed. During post-training, we curate a dataset of 130K verifiable mathematics and programming problems for reinforcement learning, integrating a test-difficulty-driven code-reward scheme to alleviate sparse-reward issues and employing strategic data resampling to stabilize training. Extensive evaluations show that MiMo-7B-Base possesses exceptional reasoning potential, outperforming even much larger 32B models. The final RL-tuned model, MiMo-7B-RL, achieves superior performance on mathematics, code and general reasoning tasks, surpassing the performance of OpenAI o1-mini. The model checkpoints are available at https://github.com/xiaomimimo/MiMo.
The automated summarisation of long legal documents can be a great aid for legal experts in their daily work. We automatically create summaries (guiding principles) of German judgments by fine-tuning a decoder-based large language model. We enrich the judgments with information about legal entities before the training. For the evaluation of the created summaries, we define a set of evaluation classes which allows us to measure their language, pertinence, completeness and correctness. Our results show that employing legal entities helps the generative model to find the relevant content, but the quality of the created summaries is not yet sufficient for a use in practice.
This paper presents a chatbot-based system to engage young Spanish people in the awareness of certain mental disorders through a self-disclosure technique. The study was carried out in a population of teenagers aged between 12 and 18 years. The dialogue engine mixes closed and open conversations, so certain controlled messages are sent to focus the chat on a specific disorder, which will change over time. Once a set of trial questions is answered, the system can initiate the conversation on the disorder under the focus according to the user's sensibility to that disorder, in an attempt to establish a more empathetic communication. Then, an open conversation based on the GPT-3 language model is initiated, allowing the user to express themselves with more freedom. The results show that these systems are of interest to young people and could help them become aware of certain mental disorders.