Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant challenges, especially when handling long sequences.This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference. Unlike existing approaches that optimize the memory based on the sequence length, we identify substantial redundancy in the channel dimension of the KV cache, as indicated by an uneven magnitude distribution and a low-rank structure in the attention weights.In response, we propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels. Our approach not only maintains or enhances model accuracy but also achieves a reduction in KV cache memory costs by over 20\% compared with vanilla KV cache eviction and quantization methods. For instance, ThinK integrated with KIVI can achieve $2.8\times$ peak memory reduction while maintaining nearly the same quality, enabling a batch size increase from 4$\times$ (with KIVI alone) to 5$\times$ when using a single GPU. Extensive evaluations on the LLaMA and Mistral models across various long-sequence datasets verified the efficiency of ThinK. Our code has been made available at https://github.com/SalesforceAIResearch/ThinK.
论文检索
输入标题、作者或关键词，从 12,113 篇学术成果中精准定位
Probabilistic Methods · Variational Inference
The success of deep learning requires large datasets and extensive training, which can create significant computational challenges. To address these challenges, pseudo-coresets, small learnable datasets that mimic the entire data, have been proposed. Bayesian Neural Networks, which offer predictive uncertainty and probabilistic interpretation for deep neural networks, also face issues with large-scale datasets due to their high-dimensional parameter space. Prior works on Bayesian Pseudo-Coresets (BPC) attempt to reduce the computational load for computing weight posterior distribution by a small number of pseudo-coresets but suffer from memory inefficiency during BPC training and sub-optimal results. To overcome these limitations, we propose Variational Bayesian Pseudo-Coreset (VBPC), a novel approach that utilizes variational inference to efficiently approximate the posterior distribution, reducing memory usage and computational costs while improving performance across benchmark datasets.
Deep Learning · Large Language Models
A popular approach to building agents using Language Models (LMs) involves iteratively prompting the LM, reflecting on its outputs, and updating the input prompts until the desired task is achieved. However, our analysis reveals two key shortcomings in the existing methods: $(i)$ limited exploration of the decision space due to repetitive reflections, which result in redundant inputs, and $(ii)$ an inability to leverage insights from previously solved tasks. To address these issues, we introduce DoT (Diversity of Thoughts), a novel framework that a) explicitly reduces redundant reflections to enhance decision-space exploration, and b) incorporates a task-agnostic memory component to enable knowledge retrieval from previously solved tasks—unlike current approaches that operate in isolation for each task. Through extensive experiments on a suite of programming benchmarks (HumanEval, MBPP, and LeetCodeHardGym) using a variety of LMs, DoT demonstrates up to a $\textbf{10}$% improvement in Pass@1 while maintaining cost-effectiveness. Furthermore, DoT is modular by design. For instance, when the diverse reflection module of DoT is integrated with existing methods like Tree of Thoughts (ToT), we observe a significant $\textbf{13}$% improvement on Game of 24 (one of the main benchmarks of ToT), highlighting the broad applicability and impact of our contributions across various reasoning tasks.
Applications · Everything Else
We introduce an extensive new dataset of MIDI files, created by transcribing audio recordings of piano performances into their constituent notes. The data pipeline we use is multi-stage, employing a language model to autonomously crawl and score audio recordings from the internet based on their metadata, followed by a stage of pruning and segmentation using an audio classifier. The resulting dataset contains over one million distinct MIDI files, comprising roughly 100,000 hours of transcribed audio. We provide an in-depth analysis of our techniques, offering statistical insights, and investigate the content by extracting metadata tags, which we also provide. Dataset available at https://github.com/loubbrad/aria-midi.
This blog post aims to evaluate how well the most capable open-source long context large language models (LLMs) utilize context, using the Needle In A Haystack test. We adopt the task of chapter summarization for recently published books to minimize data contamination while ensuring a challenging test. Our results show that open-source models still have room to improve in context utilization compared to close-source models..
Applications · Genetics, Cell Biology, Health, etc
RNA secondary structure prediction is critical for understanding RNA functionbut remains challenging due to complex structural elements like pseudoknots andlimited training data. We introduce DEPfold, a novel deep learning approach thatre-frames RNA secondary structure prediction as a dependency parsing problem.DEPfold presents three key innovations: (1) a biologically motivated transformation of RNA structures into labeled dependency trees, (2) a biaffine attentionmechanism for joint prediction of base pairings and their types, and (3) an optimaltree decoding algorithm that enforces valid RNA structural constraints. Unlike traditional energy-based methods, DEPfold learns directly from annotated data andleverages pretrained language models to predict RNA structure. We evaluate DEPfold on both within-family and cross-family RNA datasets, demonstrating significant performance improvements over existing methods. DEPfold shows strongperformance in cross-family generalization when trained on data augmented bytraditional energy-based models, outperforming existing methods on the bpRNAnew dataset. This demonstrates DEPfold’s ability to effectively learn structuralinformation beyond what traditional methods capture. Our approach bridges natural language processing (NLP) with RNA biology, providing a computationallyefficient and adaptable tool for advancing RNA structure prediction and analysis
Optimization · Zero-order and Black-box Optimization
Bayesian optimization devolves the global optimization of a costly objective function to the global optimization of a sequence of acquisition functions. This inner-loop optimization can be catastrophically difficult if it involves posterior sample paths, especially in higher dimensions. We introduce an efficient global optimization strategy for posterior samples based on global rootfinding. It provides gradient-based optimizers with two sets of judiciously selected starting points, designed to combine exploration and exploitation. The number of starting points can be kept small without sacrificing optimization quality. Remarkably, even with just one point from each set, the global optimum is discovered most of the time. The algorithm scales practically linearly to high dimensions, breaking the curse of dimensionality. For Gaussian process Thompson sampling (GP-TS), we demonstrate remarkable improvement in both inner- and outer-loop optimization, surprisingly outperforming alternatives like EI and GP-UCB in most cases. Our approach also improves the performance of other posterior sample-based acquisition functions, such as variants of entropy search. Furthermore, we propose a sample-average formulation of GP-TS, which has a parameter to explicitly control exploitation and can be computed at the cost of one posterior sample.
Reinforcement Learning · Online
We introduce Diffusion Policy Policy Optimization, DPPO, an algorithmic framework including best practices for fine-tuning diffusion-based policies (e.g. Diffusion Policy) in continuous control and robot learning tasks using the policy gradient (PG) method from reinforcement learning (RL). PG methods are ubiquitous in training RL policies with other policy parameterizations; nevertheless, they had been conjectured to be less efficient for diffusion-based policies. Surprisingly, we show that DPPO achieves the strongest overall performance and efficiency for fine-tuning in common benchmarks compared to other RL methods for diffusion-based policies and also compared to PG fine-tuning of other policy parameterizations. Through experimental investigation, we find that DPPO takes advantage of unique synergies between RL fine-tuning and the diffusion parameterization, leading to structured and on-manifold exploration, stable training, and strong policy robustness. We further demonstrate the strengths of DPPO in a range of realistic settings, including simulated robotic tasks with pixel observations, and via zero-shot deployment of simulation-trained policies on robot hardware in a long-horizon, multi-stage manipulation task.
Applications · Computer Vision
Skeletal sequence data, as a widely employed representation of human actions, are crucial in Human Activity Recognition (HAR). Recently, adversarial attacks have been proposed in this area, which exposes potential security concerns, and more importantly provides a good tool for model robustness test. Within this research, transfer-based attack is an important tool as it mimics the real-world scenario where an attacker has no knowledge of the target model, but is under-explored in Skeleton-based HAR (S-HAR). Consequently, existing S-HAR attacks exhibit weak adversarial transferability and the reason remains largely unknown. In this paper, we investigate this phenomenon via the characterization of the loss function. We find that one prominent indicator of poor transferability is the low smoothness of the loss function. Led by this observation, we improve the transferability by properly smoothening the loss when computing the adversarial examples. This leads to the first Transfer-based Attack on Skeletal Action Recognition, TASAR. TASAR explores the smoothened model posterior of pre-trained surrogates, which is achieved by a new post-train Dual Bayesian optimization strategy. Furthermore, unlike existing transfer-based methods which overlook the temporal coherence within sequences, TASAR incorporates motion dynamics into the Bayesian attack, effectively disrupting the spatial-temporal coherence of S-HARs. For exhaustive evaluation, we build the first large-scale robust S-HAR benchmark, comprising 7 S-HAR models, 10 attack methods, 3 S-HAR datasets and 2 defense models. Extensive results demonstrate the superiority of TASAR. Our benchmark enables easy comparisons for future studies, with the code available in the https://github.com/yunfengdiao/Skeleton-Robustness-Benchmark.
Reinforcement Learning · Deep RL
Real-world sequential decision-making tasks often require balancing trade-offs between multiple conflicting objectives, making Multi-Objective Reinforcement Learning (MORL) an increasingly prominent field of research. Despite recent advances, existing MORL literature has narrowly focused on performance within static environments, neglecting the importance of generalizing across diverse settings. Conversely, existing research on generalization in RL has always assumed scalar rewards, overlooking the inherent multi-objectivity of real-world problems. Generalization in the multi-objective context is fundamentally more challenging, as it requires learning a Pareto set of policies addressing varying preferences across multiple objectives. In this paper, we formalize the concept of generalization in MORL and how it can be evaluated. We then contribute a novel benchmark featuring diverse multi-objective domains with parameterized environment configurations to facilitate future studies in this area. Our baseline evaluations of state-of-the-art MORL algorithms on this benchmark reveals limited generalization capabilities, suggesting significant room for improvement. Our empirical findings also expose limitations in the expressivity of scalar rewards, emphasizing the need for multi-objective specifications to achieve effective generalization. We further analyzed the algorithmic complexities within current MORL approaches that could impede the transfer in performance from the single- to multiple-environment settings. This work fills a critical gap and lays the groundwork for future research that brings together two key areas in reinforcement learning: solving multi-objective decision-making problems and generalizing across diverse environments. We make our code available at [https://github.com/JaydenTeoh/MORL-Generalization](https://github.com/JaydenTeoh/MORL-Generalization).
Applications · Robotics
Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior.As models are becoming larger to capture more complex capabilities, their computational demands increase, as shown by recent scaling laws. Therefore, continuing with the current architectures will present a computational roadblock. To address this gap, we propose Mixture-of-Denoising Experts (MoDE) as a novel policy for Imitation Learning.MoDE surpasses current state-of-the-art Transformer-based Diffusion Policies while enabling parameter-efficient scaling through sparse experts and noise-conditioned routing, reducing both active parameters by 40\% and inference costs by 90\% via expert caching.Our architecture combines this efficient scaling with noise-conditioned self-attention mechanism, enabling more effective denoising across different noise levels. MoDE achieves state-of-the-art performance on 134 tasks in four established imitation learning benchmarks (CALVIN and LIBERO). Notably, by pretraining MoDE on diverse robotics data, we achieve 4.01 on CALVIN ABC and 0.95 on LIBERO-90. It surpasses both CNN-based and Transformer Diffusion Policies by an average of $57\%$ across 4 benchmarks, while using 90\% fewer FLOPs and fewer active parameters compared to default Diffusion Transformer architectures. Furthermore, we conduct comprehensive ablations on MoDE's components, providing insights for designing efficient and scalable Transformer architectures for Diffusion Policies. Code and demonstrations are available at https://mbreuss.github.io/MoDE_Diffusion_Policy.
Applications · Physics
(Partial) differential equations (PDEs) are fundamental tools for describing natural phenomena, making their solution crucial in science and engineering. While traditional methods, such as the finite element method, provide reliable solutions, their accuracy is often tied to the use of computationally intensive fine meshes. Moreover, they do not naturally account for measurements or prior solutions, and any change in the problem parameters requires results to be fully recomputed. Neural network-based approaches, such as physics-informed neural networks and neural operators, offer a mesh-free alternative by directly fitting those models to the PDE solution. They can also integrate prior knowledge and tackle entire families of PDEs by simply aggregating additional training losses. Nevertheless, they are highly sensitive to hyperparameters such as collocation points and the weights associated with each loss. This paper addresses these challenges by developing a science-constrained learning (SCL) framework. It demonstrates that finding a (weak) solution of a PDE is equivalent to solving a constrained learning problem with worst-case losses. This explains the limitations of previous methods that minimize the expected value of aggregated losses. SCL also organically integrates structural constraints (e.g., invariances) and (partial) measurements or known solutions. The resulting constrained learning problems can be tackled using a practical algorithm that yields accurate solutions across a variety of PDEs, neural network architectures, and prior knowledge levels without extensive hyperparameter tuning and sometimes even at a lower computational cost.
Theory · Game Theory
Mean field games (MFGs) model interactions in large-population multi-agent systems through population distributions. Traditional learning methods for MFGs are based on fixed-point iteration (FPI), where policy updates and induced population distributions are computed separately and sequentially. However, FPI-type methods may suffer from inefficiency and instability due to potential oscillations caused by this forward-backward procedure. In this work, we propose a novel perspective that treats the policy and population as a unified parameter controlling the game dynamics. By applying stochastic parameter approximation to this unified parameter, we develop SemiSGD, a simple stochastic gradient descent (SGD)-type method, where an agent updates its policy and population estimates simultaneously and fully asynchronously. Building on this perspective, we further apply linear function approximation (LFA) to the unified parameter, resulting in the first population-aware LFA (PA-LFA) for learning MFGs on continuous state-action spaces. A comprehensive finite-time convergence analysis is provided for SemiSGD with PA-LFA, including its convergence to the equilibrium for linear MFGs—a class of MFGs with a linear structure concerning the population—under the standard contractivity condition, and to a neighborhood of the equilibrium under a more practical condition. We also characterize the approximation error for non-linear MFGs. We validate our theoretical findings with six experiments on three MFGs.
Deep Learning · Large Language Models
Large Language Models fine-tuned with Reinforcement Learning from Human Feedback (RLHF-LLMs) can over-rely on aligned preferences without truly gaining self-knowledge, leading to hallucination and biases. If an LLM can better access its knowledge and know what it knows, it can avoid making false or unsupported claims. Therefore, it is crucial to evaluate whether LLMs have the ability to know what they know, as it can help to ensure accuracy and faithfulness in real-world applications. Inspired by research in Educational Psychology, surface learners who don’t really know are easily affected by teacher and peer guidance, we treat LLM as a student, incorporate role guidance in prompts to explore whether LLMs really know. Specifically, we propose a novel strategy called Role-Guided and Self-Reflection (RoSe) to fully assess whether LLM “knows it knows”. We introduce multiple combinations of different roles and strong reminder in prompts combined with self-reflection to explore what local information in prompt LLMs rely on and whether LLMs remain unaffected by external guidance with varying roles. Our findings reveal that LLMs are very sensitive to the strong reminder information. Role guidance can help LLMs reduce their reliance on strong reminder. Meanwhile, LLMs tend to trust the role of authority more when guided by different roles. Following these findings, we propose a double-calibrated strategy with verbalized confidence to extract well-calibrated data from closed-source LLM and fine-tune open-source LLMs. Extensive experiments conducted on fine-tuning open-source LLMs demonstrate the effectiveness of double-calibrated strategy in mitigating the reliance of LLMs on local information. For a thorough comparison, we not only employ public JEC-QA and openBookQA datasets, but also construct EG-QA which contains English Grammar multiple-choice question-answering and 14 key knowledge points for assessing self-knowledge and logical reasoning.
Social Aspects · Trustworthy Machine Learning
While retrieval-augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or irrelevant information. A common detection strategy involves prompting the LLM again to assess whether its response is grounded in the retrieved evidence, but this approach is costly. Alternatively, lightweight natural language inference (NLI) models for efficient grounding verification can be used at inference time. While existing pre-trained NLI models offer potential solutions, their performance remains subpar compared to larger models on realistic RAG inputs. RAG inputs are more complex than most datasets used for training NLI models and have characteristics specific to the underlying knowledge base, requiring adaptation of the NLI models to a specific target domain. Additionally, the lack of labeled instances in the target domain makes supervised domain adaptation, e.g., through fine-tuning, infeasible. To address these challenges, we introduce Automatic Generative Domain Adaptation (Auto-GDA). Our framework enables unsupervised domain adaptation through synthetic data generation.Unlike previous methods that rely on handcrafted filtering and augmentation strategies, Auto-GDA employs an iterative process to continuously improve the quality of generated samples using weak labels from less efficient teacher models and discrete optimization to select the most promising augmented samples. Experimental results demonstrate the effectiveness of our approach, with models fine-tuned on synthetic data using Auto-GDA often surpassing the performance of the teacher model and reaching the performance level of LLMs at 10% of their computational cost.
Social Aspects · Accountability, Transparency and Interpretability
Recent research has developed a number of eXplainable AI (XAI) techniques, such as gradient-based approaches, input perturbation-base methods, and black-box explanation methods. While these XAI techniques can extract meaningful insights from deep learning models, how to properly evaluate them remains an open problem. The most widely used approach is to perturb or even remove what the XAI method considers to be the most important features in an input and observe the changes in the output prediction. This approach, although straightforward, suffers the Out-of-Distribution (OOD) problem as the perturbed samples may no longer follow the original data distribution. A recent method RemOve And Retrain (ROAR) solves the OOD issue by retraining the model with perturbed samples guided by explanations. However, using the model retrained based on XAI methods to evaluate these explainers may cause information leakage and thus lead to unfair comparisons. We propose Fine-tuned Fidelity (F-Fidelity), a robust evaluation framework for XAI, which utilizes i) an explanation-agnostic fine-tuning strategy, thus mitigating the information leakage issue, and ii) a random masking operation that ensures that the removal step does not generate an OOD input. We also design controlled experiments with state-of-the-art (SOTA) explainers and their degraded version to verify the correctness of our framework. We conduct experiments on multiple data modalities, such as images, time series, and natural language. The results demonstrate that F-Fidelity significantly improves upon prior evaluation metrics in recovering the ground-truth ranking of the explainers. Furthermore, we show both theoretically and empirically that, given a faithful explainer, F-Fidelity metric can be used to compute the sparsity of influential input components, i.e., to extract the true explanation size.
Probabilistic Methods · Monte Carlo and Sampling Methods
Large language models (LLMs) can suffer from hallucinations when generating text. These hallucinations impede various applications in society and industry by making LLMs untrustworthy. Current LLMs generate text in an autoregressive fashion by predicting and appending text tokens. When an LLM is uncertain about the semantic meaning of the next tokens to generate, it is likely to start hallucinating. Thus, it has been suggested that predictive uncertainty is one of the main causes of hallucinations. We introduce Semantically Diverse Language Generation (SDLG) to quantify predictive uncertainty in LLMs. SDLG steers the LLM to generate semantically diverse yet likely alternatives for an initially generated text. This approach provides a precise measure of aleatoric semantic uncertainty, detecting whether the initial text is likely to be hallucinated. Experiments on question-answering tasks demonstrate that SDLG consistently outperforms existing methods while being the most computationally efficient, setting a new standard for uncertainty estimation in LLMs.
Deep Learning · Large Language Models
Large Language Models (LLMs) suffer from hallucinations, referring to the non-factual information in generated content, despite their superior capacities across tasks. Meanwhile, knowledge editing has been developed as a new popular paradigm to correct erroneous factual knowledge encoded in LLMs with the advantage of avoiding retraining from scratch. However, a common issue of existing evaluation datasets for knowledge editing is that they do not ensure that LLMs actually generate hallucinated answers to the evaluation questions before editing. When LLMs are evaluated on such datasets after being edited by different techniques, it is hard to directly adopt the performance to assess the effectiveness of different knowledge editing methods in correcting hallucinations. Thus, the fundamental question remains insufficiently validated: Can knowledge editing really correct hallucinations in LLMs? We proposed HalluEditBench to holistically benchmark knowledge editing methods in correcting real-world hallucinations. First, we rigorously construct a massive hallucination dataset with 9 domains, 26 topics and more than 6,000 hallucinations. Then, we assess the performance of knowledge editing methods in a holistic way on five dimensions including Efficacy, Generalization, Portability, Locality, and Robustness. Through HalluEditBench, we have provided new insights into the potentials and limitations of different knowledge editing methods in correcting hallucinations, which could inspire future improvements and facilitate progress in the field of knowledge editing.
Deep Learning · Large Language Models
Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However, existing benchmarks often fall short, either lacking extensive coverage of undergraduate-level mathematical problems or probably suffering from test-set contamination. To address these issues, we introduce UGMathBench, a diverse and dynamic benchmark specifically designed for evaluating undergraduate-level mathematical reasoning with LLMs. UGMathBench comprises 5,062 problems across 16 subjects and 111 topics, featuring 10 distinct answer types. Each problem includes three randomized versions, with additional versions planned for release as the leading open-source LLMs become saturated in UGMathBench. Furthermore, we propose two key metrics: effective accuracy (EAcc), which measures the percentage of correctly solved problems across all three versions, and reasoning gap ($\Delta$), which assesses reasoning robustness by calculating the difference between the average accuracy across all versions and EAcc. Our extensive evaluation of 23 leading LLMs reveals that the highest EAcc achieved is 56.3% by OpenAI-o1-mini, with large $\Delta$ values observed across different models. This highlights the need for future research aimed at developing "large reasoning models" with high EAcc and $\Delta = 0$. We anticipate that the release of UGMathBench, along with its detailed evaluation codes, will serve as a valuable resource to advance the development of LLMs in solving mathematical problems.
Deep Learning · Large Language Models
Math Word Problems (MWPs) play a vital role in assessing the capabilities of Large Language Models (LLMs), yet current research primarily focuses on questions with concise contexts. The impact of longer contexts on mathematical reasoning remains under-explored. This study pioneers the investigation of Context Length Generalizability (CoLeG), which refers to the ability of LLMs to solve MWPs with extended narratives. We introduce Extended Grade-School Math (E-GSM), a collection of MWPs featuring lengthy narratives, and propose two novel metrics to evaluate the efficacy and resilience of LLMs in tackling these problems. Our analysis of existing zero-shot prompting techniques with proprietary LLMs along with open-source LLMs reveals a general deficiency in CoLeG. To alleviate these issues, we propose tailored approaches for different categories of LLMs. For proprietary LLMs, we introduce a new instructional prompt designed to mitigate the impact of long contexts. For open-source LLMs, we develop a novel auxiliary task for fine-tuning to enhance CoLeG. Our comprehensive results demonstrate the effectiveness of our proposed methods, showing improved performance on E-GSM. Additionally, we conduct an in-depth analysis to differentiate the effects of semantic understanding and reasoning efficacy, showing that our methods improves the latter. We also establish the generalizability of our methods across several other MWP benchmarks. Our findings highlight the limitations of current LLMs and offer practical solutions correspondingly, paving the way for further exploration of model generalizability and training methodologies.