Fantastic LLMs for Preference Data Annotation and How to (not) Find Them

Preference tuning of large language models (LLMs) relies on high-quality human preference data, which is often expensive and time-consuming to gather. While existing methods can use trained reward models or proprietary model as judges for preference annotation, they have notable drawbacks: training reward models remain dependent on initial human data, and using proprietary model imposes license restrictions that inhibits commercial usage. In this paper, we introduce customized density ratio (CDR) that leverages open-source LLMs for data annotation, offering an accessible and effective solution. Our approach uses the log-density ratio between a well-aligned LLM and a less aligned LLM as a reward signal. We explores 221 different LLMs pairs and empirically demonstrate that increasing the performance gap between paired LLMs correlates with better reward generalization. Furthermore, we show that tailoring the density ratio reward function with specific criteria and preference exemplars enhances performance across domains and within target areas. In our experiment using density ratio from a pair of Mistral-7B models, CDR achieves a RewardBench score of 82.6, outperforming the best in-class trained reward functions and demonstrating competitive performance against SoTA models in Safety (91.0) and Reasoning (88.0) domains. We use CDR to annotate an on-policy preference dataset with which we preference tune Llama-3-8B-Instruct with SimPO. The final model achieves a 37.4% (+15.1%) win rate on ArenaHard and a 40.7% (+17.8%) win rate on Length-Controlled AlpacaEval 2.0, along with a score of 8.0 on MT-Bench.

Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model

Sequential recommendation (SR) aims to predict items that users may be interested in based on their historical behavior sequences. We revisit SR from a novel information-theoretic perspective and find that conventional sequential modeling methods fail to adequately capture the randomness and unpredictability of user behavior. Inspired by fuzzy information processing theory, this paper introduces the DDSR model, which uses fuzzy sets of interaction sequences to overcome the limitations and better capture the evolution of users' real interests. Formally based on diffusion transition processes in discrete state spaces, which is unlike common diffusion models such as DDPM that operate in continuous domains. It is better suited for discrete data, using structured transitions instead of arbitrary noise introduction to avoid information loss. Additionally, to address the inefficiency of matrix transformations due to the vast discrete space, we use semantic labels derived from quantization or RQ-VAE to replace item IDs, enhancing efficiency and improving cold start issues. Testing on three public benchmark datasets shows that DDSR outperforms existing state-of-the-art methods in various settings, demonstrating its potential and effectiveness in handling SR tasks.

Towards Convexity in Anomaly Detection: A New Formulation of SSLM with Unique Optimal Solutions

An unsolved issue in widely used methods such as Support Vector Data Description (SVDD) and Small Sphere and Large Margin SVM (SSLM) for anomaly detection is their nonconvexity, which hampers the analysis of optimal solutions in a manner similar to SVMs and limits their applicability in large-scale scenarios. In this paper, we introduce a novel convex SSLM formulation which has been demonstrated to revert to a convex quadratic programming problem for hyperparameter values of interest. Leveraging the convexity of our method, we derive numerous results that are unattainable with traditional nonconvex approaches. We conduct a thorough analysis of how hyperparameters influence the optimal solution, pointing out scenarios where optimal solutions can be trivially found and identifying instances of ill-posedness. Most notably, we establish connections between our method and traditional approaches, providing a clear determination of when the optimal solution is unique -- a task unachievable with traditional nonconvex methods. We also derive the {\nu}-property to elucidate the interactions between hyperparameters and the fractions of support vectors and margin errors in both positive and negative classes.

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning and convergence. We consider the slicing privacy mechanism that injects noise into random low-dimensional projections of the private data, and provide strong privacy guarantees for it. These noisy projections are used for training generative models. To enable optimizing generative models using this DP approach, we introduce the smoothed-sliced $f$-divergence and show it enjoys statistical consistency. Moreover, we present a kernel-based estimator for this divergence, circumventing the need for adversarial training. Extensive numerical experiments demonstrate that our approach can generate synthetic data of higher quality compared with baselines. Beyond performance improvement, our method, by sidestepping the need for noisy gradients, offers data scientists the flexibility to adjust generator architecture and hyper-parameters, run the optimization over any number of epochs, and even restart the optimization process -- all without incurring additional privacy costs.

Synthetic Data Generation for Residential Load Patterns via Recurrent GAN and Ensemble Method

Generating synthetic residential load data that can accurately represent actual electricity consumption patterns is crucial for effective power system planning and operation. The necessity for synthetic data is underscored by the inherent challenges associated with using real-world load data, such as privacy considerations and logistical complexities in large-scale data collection. In this work, we tackle the above-mentioned challenges by developing the Ensemble Recurrent Generative Adversarial Network (ERGAN) framework to generate high-fidelity synthetic residential load data. ERGAN leverages an ensemble of recurrent Generative Adversarial Networks, augmented by a loss function that concurrently takes into account adversarial loss and differences between statistical properties. Our developed ERGAN can capture diverse load patterns across various households, thereby enhancing the realism and diversity of the synthetic data generated. Comprehensive evaluations demonstrate that our method consistently outperforms established benchmarks in the synthetic generation of residential load data across various performance metrics including diversity, similarity, and statistical measures. The findings confirm the potential of ERGAN as an effective tool for energy applications requiring synthetic yet realistic load data. We also make the generated synthetic residential load patterns publicly available.

A Prompt Refinement-based Large Language Model for Metro Passenger Flow Forecasting under Delay Conditions

Accurate short-term forecasts of passenger flow in metro systems under delay conditions are crucial for emergency response and service recovery, which pose significant challenges and are currently under-researched. Due to the rare occurrence of delay events, the limited sample size under delay condictions make it difficult for conventional models to effectively capture the complex impacts of delays on passenger flow, resulting in low forecasting accuracy. Recognizing the strengths of large language models (LLMs) in few-shot learning due to their powerful pre-training, contextual understanding, ability to perform zero-shot and few-shot reasoning, to address the issues that effectively generalize and adapt with minimal data, we propose a passenger flow forecasting framework under delay conditions that synthesizes an LLM with carefully designed prompt engineering. By Refining prompt design, we enable the LLM to understand delay event information and the pattern from historical passenger flow data, thus overcoming the challenges of passenger flow forecasting under delay conditions. The propmpt engineering in the framework consists of two main stages: systematic prompt generation and prompt refinement. In the prompt generation stage, multi-source data is transformed into descriptive texts understandable by the LLM and stored. In the prompt refinement stage, we employ the multidimensional Chain of Thought (CoT) method to refine the prompts. We verify the proposed framework by conducting experiments using real-world datasets specifically targeting passenger flow forecasting under delay conditions of Shenzhen metro in China. The experimental results demonstrate that the proposed model performs particularly well in forecasting passenger flow under delay conditions.

MambaBEV: An efficient 3D detection model with Mamba2

A stable 3D object detection model based on BEV paradigm with temporal information is very important for autonomous driving systems. However, current temporal fusion model use convolutional layer or deformable self-attention is not conducive to the exchange of global information of BEV space and has more computational cost. Recently, a newly proposed based model specialized in processing sequence called mamba has shown great potential in multiple downstream task. In this work, we proposed a mamba2-based BEV 3D object detection model named MambaBEV. We also adapt an end to end self driving paradigm to test the performance of the model. Our work performs pretty good results on nucences datasets:Our base version achieves 51.7% NDS. Our code will be available soon.

Anderson Acceleration in Nonsmooth Problems: Local Convergence via Active Manifold Identification

Anderson acceleration is an effective technique for enhancing the efficiency of fixed-point iterations; however, analyzing its convergence in nonsmooth settings presents significant challenges. In this paper, we investigate a class of nonsmooth optimization algorithms characterized by the active manifold identification property. This class includes a diverse array of methods such as the proximal point method, proximal gradient method, proximal linear method, proximal coordinate descent method, Douglas-Rachford splitting (or the alternating direction method of multipliers), and the iteratively reweighted $\ell_1$ method, among others. Under the assumption that the optimization problem possesses an active manifold at a stationary point, we establish a local R-linear convergence rate for the Anderson-accelerated algorithm. Our extensive numerical experiments further highlight the robust performance of the proposed Anderson-accelerated methods.

On Calibration of LLM-based Guard Models for Reliable Content Moderation

Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails. Existing studies have developed LLM-based guard models designed to moderate the input and output of threat LLMs, ensuring adherence to safety policies by blocking content that violates these protocols upon deployment. However, limited attention has been given to the reliability and calibration of such guard models. In this work, we empirically conduct comprehensive investigations of confidence calibration for 9 existing LLM-based guard models on 12 benchmarks in both user input and model output classification. Our findings reveal that current LLM-based guard models tend to 1) produce overconfident predictions, 2) exhibit significant miscalibration when subjected to jailbreak attacks, and 3) demonstrate limited robustness to the outputs generated by different types of response models. Additionally, we assess the effectiveness of post-hoc calibration methods to mitigate miscalibration. We demonstrate the efficacy of temperature scaling and, for the first time, highlight the benefits of contextual calibration for confidence calibration of guard models, particularly in the absence of validation sets. Our analysis and experiments underscore the limitations of current LLM-based guard models and provide valuable insights for the future development of well-calibrated guard models toward more reliable content moderation. We also advocate for incorporating reliability evaluation of confidence calibration when releasing future LLM-based guard models.

BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models

While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabilities to bypass security measures and generate harmful outputs. Existing jailbreak strategies mainly focus on maximizing attack success rate (ASR), frequently neglecting other critical factors, including the relevance of the jailbreak response to the query and the level of stealthiness. This narrow focus on single objectives can result in ineffective attacks that either lack contextual relevance or are easily recognizable. In this work, we introduce BlackDAN, an innovative black-box attack framework with multi-objective optimization, aiming to generate high-quality prompts that effectively facilitate jailbreaking while maintaining contextual relevance and minimizing detectability. BlackDAN leverages Multiobjective Evolutionary Algorithms (MOEAs), specifically the NSGA-II algorithm, to optimize jailbreaks across multiple objectives including ASR, stealthiness, and semantic relevance. By integrating mechanisms like mutation, crossover, and Pareto-dominance, BlackDAN provides a transparent and interpretable process for generating jailbreaks. Furthermore, the framework allows customization based on user preferences, enabling the selection of prompts that balance harmfulness, relevance, and other factors. Experimental results demonstrate that BlackDAN outperforms traditional single-objective methods, yielding higher success rates and improved robustness across various LLMs and multimodal LLMs, while ensuring jailbreak responses are both relevant and less detectable.