CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement

Large Language Models (LLMs) have significantly advanced code generation but often require substantial resources and tend to over-generalize, limiting their efficiency for specific tasks. Fine-tuning smaller, open-source LLMs presents a viable alternative; however, it typically lags behind cutting-edge models due to supervised fine-tuning's reliance solely on correct code examples, which restricts the model's ability to learn from its own mistakes and adapt to diverse programming challenges. To bridge this gap, we introduce CodeLutra, a novel framework that enhances low-performing LLMs by leveraging both successful and failed code generation attempts. Unlike conventional fine-tuning, CodeLutra employs an iterative preference learning mechanism to compare correct and incorrect solutions as well as maximize the likelihood of correct codes. Through continuous iterative refinement, CodeLutra enables smaller LLMs to match or surpass GPT-4's performance in various code generation tasks without relying on vast external datasets or larger auxiliary models. On a challenging data analysis task, using just 500 samples improved Llama-3-8B's accuracy from 28.2% to 48.6%, approaching GPT-4's performance. These results highlight CodeLutra's potential to close the gap between open-source and closed-source models, making it a promising approach in the field of code generation.

A/B testing under Interference with Partial Network Information

A/B tests are often required to be conducted on subjects that might have social connections. For e.g., experiments on social media, or medical and social interventions to control the spread of an epidemic. In such settings, the SUTVA assumption for randomized-controlled trials is violated due to network interference, or spill-over effects, as treatments to group A can potentially also affect the control group B. When the underlying social network is known exactly, prior works have demonstrated how to conduct A/B tests adequately to estimate the global average treatment effect (GATE). However, in practice, it is often impossible to obtain knowledge about the exact underlying network. In this paper, we present UNITE: a novel estimator that relax this assumption and can identify GATE while only relying on knowledge of the superset of neighbors for any subject in the graph. Through theoretical analysis and extensive experiments, we show that the proposed approach performs better in comparison to standard estimators.

HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances

Text-to-image generative models can generate high-quality humans, but realism is lost when generating hands. Common artifacts include irregular hand poses, shapes, incorrect numbers of fingers, and physically implausible finger orientations. To generate images with realistic hands, we propose a novel diffusion-based architecture called HanDiffuser that achieves realism by injecting hand embeddings in the generative process. HanDiffuser consists of two components: a Text-to-Hand-Params diffusion model to generate SMPL-Body and MANO-Hand parameters from input text prompts, and a Text-Guided Hand-Params-to-Image diffusion model to synthesize images by conditioning on the prompts and hand parameters generated by the previous component. We incorporate multiple aspects of hand representation, including 3D shapes and joint-level finger positions, orientations and articulations, for robust learning and reliable performance during inference. We conduct extensive quantitative and qualitative experiments and perform user studies to demonstrate the efficacy of our method in generating images with high-quality hands.

SODA: Protecting Proprietary Information in On-Device Machine Learning Models

The growth of low-end hardware has led to a proliferation of machine learning-based services in edge applications. These applications gather contextual information about users and provide some services, such as personalized offers, through a machine learning (ML) model. A growing practice has been to deploy such ML models on the user's device to reduce latency, maintain user privacy, and minimize continuous reliance on a centralized source. However, deploying ML models on the user's edge device can leak proprietary information about the service provider. In this work, we investigate on-device ML models that are used to provide mobile services and demonstrate how simple attacks can leak proprietary information of the service provider. We show that different adversaries can easily exploit such models to maximize their profit and accomplish content theft. Motivated by the need to thwart such attacks, we present an end-to-end framework, SODA, for deploying and serving on edge devices while defending against adversarial usage. Our results demonstrate that SODA can detect adversarial usage with 89% accuracy in less than 50 queries with minimal impact on service performance, latency, and storage.

Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information

In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attackers can carefully curate input strings that lead to undesirable outputs. The inherent vulnerability of LLMs stems from their input-output mechanisms, especially when presented with intensely out-of-distribution (OOD) inputs. This paper proposes a token-level detection method to identify adversarial prompts, leveraging the LLM's capability to predict the next token's probability. We measure the degree of the model's perplexity and incorporate neighboring token information to encourage the detection of contiguous adversarial prompt sequences. As a result, we propose two methods: one that identifies each token as either being part of an adversarial prompt or not, and another that estimates the probability of each token being part of an adversarial prompt.

Fast Heavy Inner Product Identification Between Weights and Inputs in Neural Network Training

In this paper, we consider a heavy inner product identification problem, which generalizes the Light Bulb problem~(\cite{prr89}): Given two sets $A \subset \{-1,+1\}^d$ and $B \subset \{-1,+1\}^d$ with $|A|=|B| = n$, if there are exact $k$ pairs whose inner product passes a certain threshold, i.e., $\{(a_1, b_1), \cdots, (a_k, b_k)\} \subset A \times B$ such that $\forall i \in [k], \langle a_i,b_i \rangle \geq \rho \cdot d$, for a threshold $\rho \in (0,1)$, the goal is to identify those $k$ heavy inner products. We provide an algorithm that runs in $O(n^{2 \omega / 3+ o(1)})$ time to find the $k$ inner product pairs that surpass $\rho \cdot d$ threshold with high probability, where $\omega$ is the current matrix multiplication exponent. By solving this problem, our method speed up the training of neural networks with ReLU activation function.

Decentralized Personalized Online Federated Learning

Vanilla federated learning does not support learning in an online environment, learning a personalized model on each client, and learning in a decentralized setting. There are existing methods extending federated learning in each of the three aspects. However, some important applications on enterprise edge servers (e.g. online item recommendation at global scale) involve the three aspects at the same time. Therefore, we propose a new learning setting \textit{Decentralized Personalized Online Federated Learning} that considers all the three aspects at the same time. In this new setting for learning, the first technical challenge is how to aggregate the shared model parameters from neighboring clients to obtain a personalized local model with good performance on each client. We propose to directly learn an aggregation by optimizing the performance of the local model with respect to the aggregation weights. This not only improves personalization of each local model but also helps the local model adapting to potential data shift by intelligently incorporating the right amount of information from its neighbors. The second challenge is how to select the neighbors for each client. We propose a peer selection method based on the learned aggregation weights enabling each client to select the most helpful neighbors and reduce communication cost at the same time. We verify the effectiveness and robustness of our proposed method on three real-world item recommendation datasets and one air quality prediction dataset.

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search

Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate solution plans that execute a series of API function calls in a step-by-step manner. The multitude of candidate API function calls significantly expands the action space, amplifying the critical need for efficient action space navigation. However, existing methods either struggle with unidirectional exploration in expansive action spaces, trapped into a locally optimal solution, or suffer from exhaustively traversing all potential actions, causing inefficient navigation. To address these issues, we propose ToolChain*, an efficient tree search-based planning algorithm for LLM-based agents. It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan. By incorporating the A* search algorithm with task-specific cost function design, it efficiently prunes high-cost branches that may involve incorrect actions, identifying the most low-cost valid path as the solution. Extensive experiments on multiple tool-use and reasoning tasks demonstrate that ToolChain* efficiently balances exploration and exploitation within an expansive action space. It outperforms state-of-the-art baselines on planning and reasoning tasks by 3.1% and 3.5% on average while requiring 7.35x and 2.31x less time, respectively.

Privacy Aware Experiments without Cookies

Consider two brands that want to jointly test alternate web experiences for their customers with an A/B test. Such collaborative tests are today enabled using \textit{third-party cookies}, where each brand has information on the identity of visitors to another website. With the imminent elimination of third-party cookies, such A/B tests will become untenable. We propose a two-stage experimental design, where the two brands only need to agree on high-level aggregate parameters of the experiment to test the alternate experiences. Our design respects the privacy of customers. We propose an estimater of the Average Treatment Effect (ATE), show that it is unbiased and theoretically compute its variance. Our demonstration describes how a marketer for a brand can design such an experiment and analyze the results. On real and simulated data, we show that the approach provides valid estimate of the ATE with low variance and is robust to the proportion of visitors overlapping across the brands.

DiPS: Differentiable Policy for Sketching in Recommender Systems

In sequential recommender system applications, it is important to develop models that can capture users' evolving interest over time to successfully recommend future items that they are likely to interact with. For users with long histories, typical models based on recurrent neural networks tend to forget important items in the distant past. Recent works have shown that storing a small sketch of past items can improve sequential recommendation tasks. However, these works all rely on static sketching policies, i.e., heuristics to select items to keep in the sketch, which are not necessarily optimal and cannot improve over time with more training data. In this paper, we propose a differentiable policy for sketching (DiPS), a framework that learns a data-driven sketching policy in an end-to-end manner together with the recommender system model to explicitly maximize recommendation quality in the future. We also propose an approximate estimator of the gradient for optimizing the sketching algorithm parameters that is computationally efficient. We verify the effectiveness of DiPS on real-world datasets under various practical settings and show that it requires up to $50\%$ fewer sketch items to reach the same predictive quality than existing sketching policies.