NeurIPS 2024 Papers

How to evaluate Large Language Models (LLMs) in code generation remains an open question. Many benchmarks have been proposed, but they have two limitations, i.e., data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the latter hinders practitioners from selecting superior LLMs for specific programming domains. To address these two limitations, we propose a new benchmark - EvoCodeBench, which has the following advances: (1) Evolving data. EvoCodeBench will be dynamically updated every period (e.g., 6 months) to avoid data leakage. This paper releases the first version - EvoCodeBench-2403, containing 275 samples from 25 repositories. (2) A domain taxonomy and domain labels. Based on the statistics of open-source communities, we design a programming domain taxonomy consisting of 10 popular domains. Based on the taxonomy, we annotate each sample in EvoCodeBench with a domain label. EvoCodeBench provides a broad platform for domain-specific evaluations. (3) Domain-specific evaluations. Besides the Pass@k, we compute the Domain-Specific Improvement (DSI) and define LLMs' comfort and strange domains. These evaluations help practitioners select superior LLMs in specific domains and discover the shortcomings of existing LLMs. Besides, EvoCodeBench is collected by a rigorous pipeline and aligns with real-world repositories in multiple aspects (e.g., code distributions). We evaluate 8 popular LLMs (e.g., gpt-4, DeepSeek Coder, StarCoder 2) on EvoCodeBench and summarize some insights. EvoCodeBench reveals the actual abilities of these LLMs in real-world repositories. For example, the highest Pass@1 of gpt-4 on EvoCodeBench-2403 is only 20.74%. Besides, we evaluate LLMs in different domains and discover their comfort and strange domains. For example, gpt-4 performs best in most domains but falls behind others in the Internet domain. StarCoder 2-15B unexpectedly performs well in the Database domain and even outperforms 33B LLMs. We release EvoCodeBench, all prompts, and LLMs' completions for further community analysis.

In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety and generalize to new domains. However, existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts, leading to poor OOD detection or domain generalization performance. In this work, we aim to equip the model to generalize effectively to covariate-shift regions while precisely identifying semantic-shift regions. To achieve this, we design a novel generative augmentation method to produce coherent images that incorporate both anomaly (or novel) objects and various covariate shifts at both image and object levels. Furthermore, we introduce a training strategy that recalibrates uncertainty specifically for semantic shifts and enhances the feature extractor to align features associated with domain shifts. We validate the effectiveness of our method across benchmarks featuring both semantic and domain shifts. Our method achieves state-of-the-art performance across all benchmarks for both OOD detection and domain generalization. Code is available at https://github.com/gaozhitong/MultiShiftSeg.

Synthetic Aperture Radar (SAR) object detection has gained significant attention recently due to its irreplaceable all-weather imaging capabilities. However, this research field suffers from both limited public datasets (mostly comprising <2K images with only mono-category objects) and inaccessible source code. To tackle these challenges, we establish a new benchmark dataset and an open-source method for large-scale SAR object detection. Our dataset, SARDet-100K, is a result of intense surveying, collecting, and standardizing 10 existing SAR detection datasets, providing a large-scale and diverse dataset for research purposes. To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created. With this high-quality dataset, we conducted comprehensive experiments and uncovered a crucial challenge in SAR object detection: the substantial disparities between the pretraining on RGB datasets and finetuning on SAR datasets in terms of both data domain and model structure. To bridge these gaps, we propose a novel Multi-Stage with Filter Augmentation (MSFA) pretraining framework that tackles the problems from the perspective of data input, domain transition, and model migration. The proposed MSFA method significantly enhances the performance of SAR object detection models while demonstrating exceptional generalizability and flexibility across diverse models. This work aims to pave the way for further advancements in SAR object detection. The dataset and code is available at \url{https://github.com/zcablii/SARDet_100K}.

The need for large text corpora has increased with the advent of pretrained language models and, in particular, the discovery of scaling laws for these models. Most available corpora have sufficient data only for languages with large dominant communities. However, there is no corpus available that (i) covers a wide range of minority languages; (ii) is generated by an open-source reproducible pipeline; and (iii) is rigorously cleaned from noise, making it trustworthy to use. We present GlotCC, a clean, document-level, 2TB general domain corpus derived from CommonCrawl, covering more than 1000 languages. We make GlotCC and the system used to generate it— including the pipeline, language identification model, and filters—available to the research community. Corpus v. 1.0 https://huggingface.co/datasets/cis-lmu/GlotCC-v1 Pipeline v. 3.0 https://github.com/cisnlp/GlotCC

High-quality preference datasets are essential for training reward models that can effectively guide large language models (LLMs) in generating high-quality responses aligned with human preferences. As LLMs become stronger and better aligned, permissively licensed preference datasets, such as Open Assistant, HH-RLHF, and HelpSteer need to be updated to remain effective for reward modeling. Methods that distil preference data from proprietary LLMs such as GPT-4 have restrictions on commercial usage imposed by model providers. To improve upon both generated responses and attribute labeling quality, we release HelpSteer2, a permissively licensed preference dataset (CC-BY-4.0). Using a powerful Nemotron-4-340B base model trained on HelpSteer2, we are able to achieve the SOTA score (92.0%) on Reward-Bench's primary dataset, outperforming currently listed open and proprietary models, as of June 12th, 2024. Notably, HelpSteer2 consists of only ten thousand response pairs, an order of magnitude fewer than existing preference datasets (e.g., HH-RLHF), which makes it highly efficient for training reward models. Our extensive experiments demonstrate that reward models trained with HelpSteer2 are effective in aligning LLMs. Additionally, we propose SteerLM 2.0, a model alignment approach that can effectively make use of the rich multi-attribute score predicted by our reward models. HelpSteer2 is available at https://huggingface.co/datasets/nvidia/HelpSteer2 and code is available at https://github.com/NVIDIA/NeMo-Aligner

Recent research has highlighted the importance of data quality in scaling large language models (LLMs). However, automated data quality control faces unique challenges in collaborative settings where sharing is not allowed directly between data silos. To tackle this issue, this paper proposes a novel data quality control technique based on the notion of data influence on the training dynamics of LLMs, that high quality data are more likely to have similar training dynamics to the anchor dataset. We then leverage the influence of the training dynamics to select high-quality data from different private domains, with centralized model updates on the server side in a collaborative training fashion by either model merging or federated learning. As for the data quality indicator, we compute the per-sample gradients with respect to the private data and the anchor dataset, and use the trace of the accumulated inner products as a measurement of data quality. In addition, we develop a quality control evaluation tailored for collaborative settings with heterogeneous medical domain data. Experiments show that training on the high-quality data selected by our method can often outperform other data selection methods for collaborative fine-tuning of LLMs, across diverse private domain datasets, in medical, multilingual and financial settings.

Active Learning (AL) deals with identifying the most informative samples for labeling to reduce data annotation costs for supervised learning tasks. AL research suffers from the fact that lifts from literature generalize poorly and that only a small number of repetitions of experiments are conducted. To overcome these obstacles, we propose CDALBench, the first active learning benchmark which includes tasks in computer vision, natural language processing and tabular learning. Furthermore, by providing an efficient, greedy oracle, CDALBench can be evaluated with 50 runs for each experiment. We show, that both the cross-domain character and a large amount of repetitions are crucial for sophisticated evaluation of AL research. Concretely, we show that the superiority of specific methods varies over the different domains, making it important to evaluate Active Learning with a cross-domain benchmark. Additionally, we show that having a large amount of runs is crucial. With only conducting three runs as often done in the literature, the superiority of specific methods can strongly vary with the specific runs. This effect is so strong, that, depending on the seed, even a well-established method's performance can be significantly better and significantly worse than random for the same dataset.

In this paper, we introduce SaulLM-medium and SaulLM-large, two large language models (LLMs) families tailored for the legal sector. These models, which feature architectures of 54 billion and 140 billion parameters, respectively, are based on the Mixtral architecture. The development of SaulLM-54B and SaulLM-140B is guided by large-scale domain adaptation, divided into strategies: (1) the exploitation of continued pretaining involving a legal corpus that includes over $400$ billion tokens, (2) the implementation of a specialized legal instruction-following protocol, and (3) the alignment of model outputs with human preferences in legal interpretations. The integration of synthetically generated data in the second and third steps enhances the models' capabilities in interpreting and processing legal texts, effectively reaching state-of-the-art performance and outperforming all previous open-source models on LegalBench Instruct. This research thoroughly explores the trade-offs involved in domain-specific adaptation at this scale, offering insights that may inform future studies on domain adaptation using strong decoder models. Building upon SaulLM-7B, this study refines the approach to produce an LLM better equipped for legal tasks and domains. Additionally, we release base, instruct and aligned versions on top of SaulLM-medium and SaulLM-large under the MIT License to facilitate reuse and collaborative research.

In Open-Set Domain Generalization (OSDG), the model is exposed to both new variations of data appearance (domains) and open-set conditions, where both known and novel categories are present at test time. The challenges of this task arise from the dual need to generalize across diverse domains and accurately quantify category novelty, which is critical for applications in dynamic environments. Recently, meta-learning techniques have demonstrated superior results in OSDG, effectively orchestrating the meta-train and -test tasks by employing varied random categories and predefined domain partition strategies. These approaches prioritize a well-designed training schedule over traditional methods that focus primarily on data augmentation and the enhancement of discriminative feature learning. The prevailing meta-learning models in OSDG typically utilize a predefined sequential domain scheduler to structure data partitions. However, a crucial aspect that remains inadequately explored is the influence brought by strategies of domain schedulers during training. In this paper, we observe that an adaptive domain scheduler benefits more in OSDG compared with prefixed sequential and random domain schedulers. We propose the Evidential Bi-Level Hardest Domain Scheduler (EBiL-HaDS) to achieve an adaptive domain scheduler. This method strategically sequences domains by assessing their reliabilities in utilizing a follower network, trained with confidence scores learned in an evidential manner, regularized by max rebiasing discrepancy, and optimized in a bilevel manner. We verify our approach on three OSDG benchmarks, i.e., PACS, DigitsDG, and OfficeHome. The results show that our method substantially improves OSDG performance and achieves more discriminative embeddings for both the seen and unseen categories, underscoring the advantage of a judicious domain scheduler for the generalizability to unseen domains and unseen categories. The source code is publicly available at https://github.com/KPeng9510/EBiL-HaDS.

Large language models (LLMs) have made significant progress in natural language processing tasks and demonstrate considerable potential in the legal domain. However, legal applications demand high standards of accuracy, reliability, and fairness. Applying existing LLMs to legal systems without careful evaluation of their potential and limitations could pose significant risks in legal practice. To this end, we introduce a standardized comprehensive Chinese legal benchmark LexEval. This benchmark is notable in the following three aspects: (1) Ability Modeling: We propose a new taxonomy of legal cognitive abilities to organize different tasks. (2) Scale: To our knowledge, LexEval is currently the largest Chinese legal evaluation dataset, comprising 23 tasks and 14,150 questions. (3) Data: we utilize formatted existing datasets, exam datasets and newly annotated datasets by legal experts to comprehensively evaluate the various capabilities of LLMs. LexEval not only focuses on the ability of LLMs to apply fundamental legal knowledge but also dedicates efforts to examining the ethical issues involved in their application. We evaluated 38 open-source and commercial LLMs and obtained some interesting findings. The experiments and findings offer valuable insights into the challenges and potential solutions for developing Chinese legal systems and LLM evaluation pipelines. The LexEval dataset and leaderboard are publicly available at https://github.com/CSHaitao/LexEval and will be continuously updated.

Our world is full of varied actions and moves in specialized fields that we, as humans, seek to identify and learn about. To evaluate the effectiveness of multi-modal models in helping us recognize such fine-grained actions, we introduce ActionAtlas, a video question answering (VideoQA) benchmark on fine-grained action recognition with short videos across various sports. ActionAtlas contains 554 videos spanning 284 actions across 42 sports with 1161 actions as total potential choices. Unlike most existing action recognition benchmarks that focus on simplistic actions, often identifiable from a single frame, ActionAtlas focuses on intricate movements and tests the models' ability to discern subtle differences. Additionally, each video in ActionAtlas also includes a question, which helps to more accurately pinpoint the action's performer in scenarios where multiple individuals are involved in different activities. We evaluate proprietary and open models on this benchmark and show that the state-of-the-art models only perform at most 48.73% accurately where random chance is 20%. Furthermore, our results show that a high frame sampling rate is essential for recognizing actions in ActionAtlas, a feature that current top proprietary models like Gemini lack in their default settings.

In this paper, we introduce DCDepth, a novel framework for the long-standing monocular depth estimation task. Moving beyond conventional pixel-wise depth estimation in the spatial domain, our approach estimates the frequency coefficients of depth patches after transforming them into the discrete cosine domain. This unique formulation allows for the modeling of local depth correlations within each patch. Crucially, the frequency transformation segregates the depth information into various frequency components, with low-frequency components encapsulating the core scene structure and high-frequency components detailing the finer aspects. This decomposition forms the basis of our progressive strategy, which begins with the prediction of low-frequency components to establish a global scene context, followed by successive refinement of local details through the prediction of higher-frequency components. We conduct comprehensive experiments on NYU-Depth-V2, TOFDC, and KITTI datasets, and demonstrate the state-of-the-art performance of DCDepth. Code is available at https://github.com/w2kun/DCDepth.

Open-set Classification (OSC) is a critical requirement for safely deploying machine learning models in the open world, which aims to classify samples from known classes and reject samples from out-of-distribution (OOD). Existing methods exploit the feature space of trained network and attempt at estimating the uncertainty in the predictions. However, softmax-based neural networks are found to be overly confident in their predictions even on data they have never seen before and the immense diversity of the OOD examples also makes such methods fragile. To this end, we follow the idea of estimating the underlying density of the training data to decide whether a given input is close to the in-distribution (IND) data and adopt Energy-based models (EBMs) as density estimators. A novel energy-based generative open-set node classification method, \textit{EGonc}, is proposed to achieve open-set graph learning. Specifically, we generate substitute unknowns to mimic the distribution of real open-set samples firstly, based on the information of graph structures. Then, an additional energy logit representing the virtual OOD class is learned from the residual of the feature against the principal space, and matched with the original logits by a constant scaling. This virtual logit serves as the indicator of OOD-ness. EGonc has nice theoretical properties that guarantee an overall distinguishable margin between the detection scores for IND and OOD samples. Comprehensive experimental evaluations of EGonc also demonstrate its superiority.

Enabling deep models to generalize in non-stationary environments is vital for real-world machine learning, as data distributions are often found to continually change. Recently, evolving domain generalization (EDG) has emerged to tackle the domain generalization in a time-varying system, where the domain gradually evolves over time in an underlying continuous structure. Nevertheless, it typically assumes multiple source domains simultaneously ready. It still remains an open problem to address EDG in the domain-incremental setting, where source domains are non-static and arrive sequentially to mimic the evolution of training domains. To this end, we propose Weight Diffusion (W-Diff), a novel framework that utilizes the conditional diffusion model in the parameter space to learn the evolving pattern of classifiers during the domain-incremental training process. Specifically, the diffusion model is conditioned on the classifier weights of different historical domain (regarded as a reference point) and the prototypes of current domain, to learn the evolution from the reference point to the classifier weights of current domain (regarded as the anchor point). In addition, a domain-shared feature encoder is learned by enforcing prediction consistency among multiple classifiers, so as to mitigate the overfitting problem and restrict the evolving pattern to be reflected in the classifier as much as possible. During inference, we adopt the ensemble manner based on a great number of target domain-customized classifiers, which are cheaply obtained via the conditional diffusion model, for robust prediction. Comprehensive experiments on both synthetic and real-world datasets show the superior generalization performance of W-Diff on unseen domains in the future.