We review approaches to statistical inference based on randomization. Permutation tests are treated as an important special case. Under a certain group invariance property, referred to as the ``randomization hypothesis,'' randomization tests achieve exact control of the Type I error rate in finite samples. Although this unequivocal precision is very appealing, the range of problems that satisfy the randomization hypothesis is somewhat limited. We show that randomization tests are often asymptotically, or approximately, valid and efficient in settings that deviate from the conditions required for finite-sample error control. When randomization tests fail to offer even asymptotic Type 1 error control, their asymptotic validity may be restored by constructing an asymptotically pivotal test statistic. Randomization tests can then provide exact error control for tests of highly structured hypotheses with good performance in a wider class of problems. We give a detailed overview of several prominent applications of randomization tests, including two-sample permutation tests, regression, and conformal inference.
Inductive conformal predictors (ICPs) are algorithms that are able to generate prediction sets, instead of point predictions, which are valid at a user-defined confidence level, only assuming exchangeability. These algorithms are useful for reliable machine learning and are increasing in popularity. The ICP development process involves dividing development data into three parts: training, calibration and test. With access to limited or expensive development data, it is an open question regarding the most efficient way to divide the data. This study provides several experiments to explore this question and consider the case for allowing overlap of examples between training and calibration sets. Conclusions are drawn that will be of value to academics and practitioners planning to use ICPs.
The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential of LLM-powered agents to comprehend ambiguous user instructions for reasoning and decision-making is still under exploration. In this work, we introduce a new task, Proactive Agent Planning, which requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction, invoke external tools to collect valid information, and generate a plan to fulfill the user's demands. To study this practical problem, we establish a new benchmark dataset, Ask-before-Plan. To tackle the deficiency of LLMs in proactive planning, we propose a novel multi-agent framework, Clarification-Execution-Planning (\texttt{CEP}), which consists of three agents specialized in clarification, execution, and planning. We introduce the trajectory tuning scheme for the clarification agent and static execution agent, as well as the memory recollection mechanism for the dynamic execution agent. Extensive evaluations and comprehensive analyses conducted on the Ask-before-Plan dataset validate the effectiveness of our proposed framework.
Robot manipulation relying on learned object-centric descriptors became popular in recent years. Visual descriptors can easily describe manipulation task objectives, they can be learned efficiently using self-supervision, and they can encode actuated and even non-rigid objects. However, learning robust, view-invariant keypoints in a self-supervised approach requires a meticulous data collection approach involving precise calibration and expert supervision. In this paper we introduce Cycle-Correspondence Loss (CCL) for view-invariant dense descriptor learning, which adopts the concept of cycle-consistency, enabling a simple data collection pipeline and training on unpaired RGB camera views. The key idea is to autonomously detect valid pixel correspondences by attempting to use a prediction over a new image to predict the original pixel in the original image, while scaling error terms based on the estimated confidence. Our evaluation shows that we outperform other self-supervised RGB-only methods, and approach performance of supervised methods, both with respect to keypoint tracking as well as for a robot grasping downstream task.
Synthetic control (SC) models are widely used to estimate causal effects in settings with observational time-series data. To identify the causal effect on a target unit, SC requires the existence of correlated units that are not impacted by the intervention. Given one of these potential donor units, how can we decide whether it is in fact a valid donor - that is, one not subject to spillover effects from the intervention? Such a decision typically requires appealing to strong a priori domain knowledge specifying the units, which becomes infeasible in situations with large pools of potential donors. In this paper, we introduce a practical, theoretically-grounded donor selection procedure, aiming to weaken this domain knowledge requirement. Our main result is a Theorem that yields the assumptions required to identify donor values at post-intervention time points using only pre-intervention data. We show how this Theorem - and the assumptions underpinning it - can be turned into a practical method for detecting potential spillover effects and excluding invalid donors when constructing SCs. Importantly, we employ sensitivity analysis to formally bound the bias in our SC causal estimate in situations where an excluded donor was indeed valid, or where a selected donor was invalid. Using ideas from the proximal causal inference and instrumental variables literature, we show that the excluded donors can nevertheless be leveraged to further debias causal effect estimates. Finally, we illustrate our donor selection procedure on both simulated and real-world datasets.
The reasoning abilities of Large Language Models (LLMs) are becoming a central focus of study in NLP. In this paper, we consider the case of syllogistic reasoning, an area of deductive reasoning studied extensively in logic and cognitive psychology. Previous research has shown that pre-trained LLMs exhibit reasoning biases, such as $\textit{content effects}$, avoid answering that $\textit{no conclusion follows}$, display human-like difficulties, and struggle with multi-step reasoning. We contribute to this research line by systematically investigating the effects of chain-of-thought reasoning, in-context learning (ICL), and supervised fine-tuning (SFT) on syllogistic reasoning, considering syllogisms with conclusions that support or violate world knowledge, as well as ones with multiple premises. Crucially, we go beyond the standard focus on accuracy, with an in-depth analysis of the conclusions generated by the models. Our results suggest that the behavior of pre-trained LLMs can be explained by heuristics studied in cognitive science and that both ICL and SFT improve model performance on valid inferences, although only the latter mitigates most reasoning biases without harming model consistency.
Rigorously establishing the safety of black-box machine learning models concerning critical risk measures is important for providing guarantees about model behavior. Recently, Bates et. al. (JACM '24) introduced the notion of a risk controlling prediction set (RCPS) for producing prediction sets that are statistically guaranteed low risk from machine learning models. Our method extends this notion to the sequential setting, where we provide guarantees even when the data is collected adaptively, and ensures that the risk guarantee is anytime-valid, i.e., simultaneously holds at all time steps. Further, we propose a framework for constructing RCPSes for active labeling, i.e., allowing one to use a labeling policy that chooses whether to query the true label for each received data point and ensures that the expected proportion of data points whose labels are queried are below a predetermined label budget. We also describe how to use predictors (i.e., the machine learning model for which we provide risk control guarantees) to further improve the utility of our RCPSes by estimating the expected risk conditioned on the covariates. We characterize the optimal choices of label policy and predictor under a fixed label budget and show a regret result that relates the estimation error of the optimal labeling policy and predictor to the wealth process that underlies our RCPSes. Lastly, we present practical ways of formulating label policies and empirically show that our label policies use fewer labels to reach higher utility than naive baseline labeling strategies on both simulations and real data.
Large language models (LLMs) have demonstrated impressive task-solving capabilities, achieved through either prompting techniques or system designs. However, concerns have arisen regarding their proficiency in planning tasks, as they often struggle to generate valid plans. This paper investigates the impact of fine-tuning on LLMs' planning capabilities. Our findings indicate that LLMs can achieve good performance in planning through substantial (thousands of specific examples) fine-tuning. However, fine-tuning is associated with significant economic and computational costs. To address this challenge, we propose the Maximum Diversity Fine-Tuning (MDFT) strategy to improve the sample efficiency of fine-tuning in the planning domain. Specifically, our algorithm, referred to as MDFT-g, encodes the planning task instances with their graph representations and selects a subset of samples in the vector space that maximizes data diversity. We empirically demonstrate that MDFT-g consistently outperforms existing baselines at various scales across multiple benchmark domains.
Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets face limitations: they rely on human annotators who assess code primarily through semantic understanding rather than functional verification, leading to potential inaccuracies and scalability issues. Additionally, current evaluation metrics often overlook the multi-choice nature of code search. This paper introduces CoSQA+, pairing high-quality queries from CoSQA with multiple suitable codes. We develop an automated pipeline featuring multiple model-based candidate selections and the novel test-driven agent annotation system. Among a single Large Language Model (LLM) annotator and Python expert annotators (without test-based verification), agents leverage test-based verification and achieve the highest accuracy of 92.0%. Through extensive experiments, CoSQA+ has demonstrated superior quality over CoSQA. Models trained on CoSQA+ exhibit improved performance. We provide the code and data at https://github.com/DeepSoftwareAnalytics/CoSQA_Plus.
We develop new conformal inference methods for obtaining validity guarantees on the output of large language models (LLMs). Prior work in conformal language modeling identifies a subset of the text that satisfies a high-probability guarantee of correctness. These methods work by filtering claims from the LLM's original response if a scoring function evaluated on the claim fails to exceed a threshold calibrated via split conformal prediction. Existing methods in this area suffer from two deficiencies. First, the guarantee stated is not conditionally valid. The trustworthiness of the filtering step may vary based on the topic of the response. Second, because the scoring function is imperfect, the filtering step can remove many valuable and accurate claims. We address both of these challenges via two new conformal methods. First, we generalize the conditional conformal procedure of Gibbs et al. (2023) in order to adaptively issue weaker guarantees when they are required to preserve the utility of the output. Second, we show how to systematically improve the quality of the scoring function via a novel algorithm for differentiating through the conditional conformal procedure. We demonstrate the efficacy of our approach on biography and medical question-answering datasets.
Adverse weather conditions can severely affect the performance of LiDAR sensors by introducing unwanted noise in the measurements. Therefore, differentiating between noise and valid points is crucial for the reliable use of these sensors. Current approaches for detecting adverse weather points require large amounts of labeled data, which can be difficult and expensive to obtain. This paper proposes a label-efficient approach to segment LiDAR point clouds in adverse weather. We develop a framework that uses few-shot semantic segmentation to learn to segment adverse weather points from only a few labeled examples. Then, we use a semi-supervised learning approach to generate pseudo-labels for unlabelled point clouds, significantly increasing the amount of training data without requiring any additional labeling. We also integrate good weather data in our training pipeline, allowing for high performance in both good and adverse weather conditions. Results on real and synthetic datasets show that our method performs well in detecting snow, fog, and spray. Furthermore, we achieve competitive performance against fully supervised methods while using only a fraction of labeled data.
Travel planning is a complex task that involves generating a sequence of actions related to visiting places subject to constraints and maximizing some user satisfaction criteria. Traditional approaches rely on problem formulation in a given formal language, extracting relevant travel information from web sources, and use an adequate problem solver to generate a valid solution. As an alternative, recent Large Language Model (LLM) based approaches directly output plans from user requests using language. Although LLMs possess extensive travel domain knowledge and provide high-level information like points of interest and potential routes, current state-of-the-art models often generate plans that lack coherence, fail to satisfy constraints fully, and do not guarantee the generation of high-quality solutions. We propose TRIP-PAL, a hybrid method that combines the strengths of LLMs and automated planners, where (i) LLMs get and translate travel information and user information into data structures that can be fed into planners; and (ii) automated planners generate travel plans that guarantee constraint satisfaction and optimize for users' utility. Our experiments across various travel scenarios show that TRIP-PAL outperforms an LLM when generating travel plans.
Randomized controlled trials (RCTs) frequently utilize covariate-adaptive randomization (CAR) (e.g., stratified block randomization) and commonly suffer from imperfect compliance. This paper studies the identification and inference for the average treatment effect (ATE) and the average treatment effect on the treated (ATT) in such RCTs with a binary treatment. We first develop characterizations of the identified sets for both estimands. Since data are generally not i.i.d. under CAR, these characterizations do not follow from existing results. We then provide consistent estimators of the identified sets and asymptotically valid confidence intervals for the parameters. Our asymptotic analysis leads to concrete practical recommendations regarding how to estimate the treatment assignment probabilities that enter the estimated bounds. For the ATE bounds, using sample analog assignment frequencies is more efficient than relying on the true assignment probabilities. For the ATT bounds, the most efficient approach is to use the true assignment probability for the probabilities in the numerator and the sample analog for those in the denominator.
Event cameras are renowned for their high efficiency due to outputting a sparse, asynchronous stream of events. However, they are plagued by noisy events, especially in low light conditions. Denoising is an essential task for event cameras, but evaluating denoising performance is challenging. Label-dependent denoising metrics involve artificially adding noise to clean sequences, complicating evaluations. Moreover, the majority of these metrics are monotonic, which can inflate scores by removing substantial noise and valid events. To overcome these limitations, we propose the first label-free and non-monotonic evaluation metric, the area of the continuous contrast curve (AOCC), which utilizes the area enclosed by event frame contrast curves across different time intervals. This metric is inspired by how events capture the edge contours of scenes or objects with high temporal resolution. An effective denoising method removes noise without eliminating these edge-contour events, thus preserving the contrast of event frames. Consequently, contrast across various time ranges serves as a metric to assess denoising effectiveness. As the time interval lengthens, the curve will initially rise and then fall. The proposed metric is validated through both theoretical and experimental evidence.
Testing is essential to modern software engineering for building reliable software. Given the high costs of manually creating test cases, automated test case generation, particularly methods utilizing large language models, has become increasingly popular. These neural approaches generate semantically meaningful tests that are more maintainable compared with traditional automatic testing methods like fuzzing. However, the diversity and volume of unit tests in current datasets are limited. In this paper, we introduce a novel data augmentation technique, *FuzzAug*, that introduces the benefits of fuzzing to large language models to preserve valid program semantics and provide diverse inputs. This enhances the model's ability to embed correct inputs that can explore more branches of the function under test. Our evaluations show that models trained with dataset augmented by FuzzAug increase assertion accuracy by 5%, improve compilation rate by more than 10%, and generate unit test functions with 5% more branch coverage. This technique demonstrates the potential of using dynamic software testing to improve neural test generation, offering significant enhancements in neural test generation.
Predicting edge weights on graphs has various applications, from transportation systems to social networks. This paper describes a Graph Neural Network (GNN) approach for edge weight prediction with guaranteed coverage. We leverage conformal prediction to calibrate the GNN outputs and produce valid prediction intervals. We handle data heteroscedasticity through error reweighting and Conformalized Quantile Regression (CQR). We compare the performance of our method against baseline techniques on real-world transportation datasets. Our approach has better coverage and efficiency than all baselines and showcases robustness and adaptability.
Complex video object segmentation serves as a fundamental task for a wide range of downstream applications such as video editing and automatic data annotation. Here we present the 2nd place solution in the MOSE track of PVUW 2024. To mitigate problems caused by tiny objects, similar objects and fast movements in MOSE. We use instance segmentation to generate extra pretraining data from the valid and test set of MOSE. The segmented instances are combined with objects extracted from COCO to augment the training data and enhance semantic representation of the baseline model. Besides, motion blur is added during training to increase robustness against image blur induced by motion. Finally, we apply test time augmentation (TTA) and memory strategy to the inference stage. Our method ranked 2nd in the MOSE track of PVUW 2024, with a $\mathcal{J}$ of 0.8007, a $\mathcal{F}$ of 0.8683 and a $\mathcal{J}$\&$\mathcal{F}$ of 0.8345.
Explainable AI (XAI) has revolutionized the field of deep learning by empowering users to have more trust in neural network models. The field of XAI allows users to probe the inner workings of these algorithms to elucidate their decision-making processes. The rise in popularity of XAI has led to the advent of different strategies to produce explanations, all of which only occasionally agree. Thus several objective evaluation metrics have been devised to decide which of these modules give the best explanation for specific scenarios. The goal of the paper is twofold: (i) we employ the notions of necessity and sufficiency from causal literature to come up with a novel explanatory technique called SHifted Adversaries using Pixel Elimination(SHAPE) which satisfies all the theoretical and mathematical criteria of being a valid explanation, (ii) we show that SHAPE is, infact, an adversarial explanation that fools causal metrics that are employed to measure the robustness and reliability of popular importance based visual XAI methods. Our analysis shows that SHAPE outperforms popular explanatory techniques like GradCAM and GradCAM++ in these tests and is comparable to RISE, raising questions about the sanity of these metrics and the need for human involvement for an overall better evaluation.
Greybox fuzzing has achieved success in revealing bugs and vulnerabilities in programs. However, randomized mutation strategies have limited the fuzzer's performance on structured data. Specialized fuzzers can handle complex structured data, but require additional efforts in grammar and suffer from low throughput. In this paper, we explore the potential of utilizing the Large Language Model to enhance greybox fuzzing for structured data. We utilize the pre-trained knowledge of LLM about data conversion and format to generate new valid inputs. We further fine-tuned it with paired mutation seeds to learn structured format and mutation strategies effectively. Our LLM-based fuzzer, LLAMAFUZZ, integrates the power of LLM to understand and mutate structured data to fuzzing. We conduct experiments on the standard bug-based benchmark Magma and a wide variety of real-world programs. LLAMAFUZZ outperforms our top competitor by 41 bugs on average. We also identified 47 unique bugs across all trials. Moreover, LLAMAFUZZ demonstrated consistent performance on both bug trigger and bug reached. Compared to AFL++, LLAMAFUZZ achieved 27.19% more branches in real-world program sets on average. We also demonstrate a case study to explain how LLMs enhance the fuzzing process in terms of code coverage.
This paper investigates third-degree price discrimination under endogenous market segmentation. Segmenting a market requires access to information about consumers, and this information comes with a cost. I explore the trade-offs between the benefits of segmentation and the costs of information acquisition, revealing a non-monotonic relationship between consumer surplus and the cost of information acquisition for monopolist. I show that in some markets, allowing the monopolist easier access to customer data can also benefit customers. I also analyzed how social welfare reacts to changes in the cost level of information acquisition and showed that the non-monotonicity result is also valid in social welfare analysis.