Detecting evidence within the context is a key step in the process of reasoning task. Evaluating and enhancing the capabilities of LLMs in evidence detection will strengthen context-based reasoning performance. This paper proposes a benchmark called DetectBench for verifying the ability to detect and piece together implicit evidence within a long context. DetectBench contains 3,928 multiple-choice questions, with an average of 994 tokens per question. Each question contains an average of 4.55 pieces of implicit evidence, and solving the problem typically requires 7.62 logical jumps to find the correct answer. To enhance the performance of LLMs in evidence detection, this paper proposes Detective Reasoning Prompt and Finetune. Experiments demonstrate that the existing LLMs' abilities to detect evidence in long contexts are far inferior to humans. However, the Detective Reasoning Prompt effectively enhances the capability of powerful LLMs in evidence detection, while the Finetuning method shows significant effects in enhancing the performance of weaker LLMs. Moreover, when the abilities of LLMs in evidence detection are improved, their final reasoning performance is also enhanced accordingly.

Large Language Models (LLMs) have attained the impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data. However, collecting human-written data of high quality, especially multi-turn dialogues, is expensive and unattainable for most people. Though previous studies have used powerful LLMs to generate the dialogues automatically, they all suffer from generating untruthful dialogues because of the model hallucination. Therefore, we propose a method called RefGPT to generate enormous truthful and customized dialogues without worrying about factual errors caused by the model hallucination. RefGPT solves the model hallucination in dialogue generation by restricting the LLMs to leverage the given reference instead of reciting their own knowledge to generate dialogues. Additionally, RefGPT adds detailed controls on every utterance to enable high customization capability, which previous studies have ignored. On the basis of RefGPT, we also propose two high-quality dialogue datasets generated by GPT-4, namely RefGPT-Fact and RefGPT-Code. RefGPT-Fact is a dataset with 100k multi-turn dialogues based on factual knowledge and RefGPT-Code has 76k multi-turn dialogues covering a wide range of coding scenarios. Our code and datasets are released in https://github.com/mutonix/RefGPT.

Informal reasoning ability is the ability to reason based on common sense, experience, and intuition.Humans use informal reasoning every day to extract the most influential elements for their decision-making from a large amount of life-like information.With the rapid development of language models, the realization of general artificial intelligence has emerged with hope. Given the outstanding informal reasoning ability of humans, how much informal reasoning ability language models have has not been well studied by scholars.In order to explore the gap between humans and language models in informal reasoning ability, this paper constructs a Detective Reasoning Benchmark, which is an assembly of 1,200 questions gathered from accessible online resources, aims at evaluating the model's informal reasoning ability in real-life context.Considering the improvement of the model's informal reasoning ability restricted by the lack of benchmark, we further propose a Self-Question Prompt Framework that mimics human thinking to enhance the model's informal reasoning ability.The goals of self-question are to find key elements, deeply investigate the connections between these elements, encourage the relationship between each element and the problem, and finally, require the model to reasonably answer the problem.The experimental results show that human performance greatly outperforms the SoTA Language Models in Detective Reasoning Benchmark.Besides, Self-Question is proven to be the most effective prompt engineering in improving GPT-4's informal reasoning ability, but it still does not even surpass the lowest score made by human participants.Upon acceptance of the paper, the source code for the benchmark will be made publicly accessible.

Recommender system (RS) is an established technology with successful applications in social media, e-commerce, entertainment, and more. RSs are indeed key to the success of many popular APPs, such as YouTube, Tik Tok, Xiaohongshu, Bilibili, and others. This paper explores the methodology for improving modern industrial RSs. It is written for experienced RS engineers who are diligently working to improve their key performance indicators, such as retention and duration. The experiences shared in this paper have been tested in some real industrial RSs and are likely to be generalized to other RSs as well. Most contents in this paper are industry experience without publicly available references.

New Natural Langauge Process (NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge. Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 249,587 questions and accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results indicate that LLMs exceed average performance of humans in science, engineering, agronomy, medicine, and art, but fall short in economics, jurisprudence, pedagogy, literature, history, and management.

Online platforms often incentivize consumers to improve user engagement and platform revenue. Since different consumers might respond differently to incentives, individual-level budget allocation is an essential task in marketing campaigns. Recent advances in this field often address the budget allocation problem using a two-stage paradigm: the first stage estimates the individual-level treatment effects using causal inference algorithms, and the second stage invokes integer programming techniques to find the optimal budget allocation solution. Since the objectives of these two stages might not be perfectly aligned, such a two-stage paradigm could hurt the overall marketing effectiveness. In this paper, we propose a novel end-to-end framework to directly optimize the business goal under budget constraints. Our core idea is to construct a regularizer to represent the marketing goal and optimize it efficiently using gradient estimation techniques. As such, the obtained models can learn to maximize the marketing goal directly and precisely. We extensively evaluate our proposed method in both offline and online experiments, and experimental results demonstrate that our method outperforms current state-of-the-art methods. Our proposed method is currently deployed to allocate marketing budgets for hundreds of millions of users on a short video platform and achieves significant business goal improvements. Our code will be publicly available.

Singular value decomposition (SVD) is one of the most fundamental tools in machine learning and statistics.The modern machine learning community usually assumes that data come from and belong to small-scale device users. The low communication and computation power of such devices, and the possible privacy breaches of users' sensitive data make the computation of SVD challenging. Federated learning (FL) is a paradigm enabling a large number of devices to jointly learn a model in a communication-efficient way without data sharing. In the FL framework, we develop a class of algorithms called FedPower for the computation of partial SVD in the modern setting. Based on the well-known power method, the local devices alternate between multiple local power iterations and one global aggregation to improve communication efficiency. In the aggregation, we propose to weight each local eigenvector matrix with Orthogonal Procrustes Transformation (OPT). Considering the practical stragglers' effect, the aggregation can be fully participated or partially participated, where for the latter we propose two sampling and aggregation schemes. Further, to ensure strong privacy protection, we add Gaussian noise whenever the communication happens by adopting the notion of differential privacy (DP). We theoretically show the convergence bound for FedPower. The resulting bound is interpretable with each part corresponding to the effect of Gaussian noise, parallelization, and random sampling of devices, respectively. We also conduct experiments to demonstrate the merits of FedPower. In particular, the local iterations not only improve communication efficiency but also reduce the chance of privacy breaches.

Decentralized optimization has been demonstrated to be very useful in machine learning. This work studies the communication-efficiency issue in decentralized optimization. We analyze the Periodic Decentralized Stochastic Gradient Descent (PD-SGD) algorithm, a straightforward combination of federated averaging and decentralized SGD. For the setting of for non-convex objective and non-identically distributed data, we prove that PD-SGD converges to a critical point. In particular, the number of local SGDs trades off communication and local computation. From an algorithmic perspective, we analyze a novel version of PD-SGD, which alternates between multiple local updates and multiple decentralized SGDs. We also show that when we periodically shrink the length of local updates, this generalized PD-SGD can better balance the communication-convergence trade-off both theoretically and empirically.

Collaborative machine learning (ML), also known as federated ML, allows participants to jointly train a model without data sharing. To update the model parameters, the central parameter server broadcasts model parameters to the participants, and the participants send ascending directions such as gradients to the server. While data do not leave a participant's device, the communicated gradients and parameters will leak a participant's privacy. Prior work proposed attacks that infer participant's privacy from gradients and parameters, and they showed simple defenses like dropout and differential privacy do not help much. To defend privacy leakage, we propose a method called Double Blind Collaborative Learning (DBCL) which is based on random matrix sketching. The high-level idea is to apply a random transformation to the parameters, data, and gradients in every iteration so that the existing attacks will fail or become less effective. While it improves the security of collaborative ML, DBCL does not increase the computation and communication cost much and does not hurt prediction accuracy at all. DBCL can be potentially applied to decentralized collaborative ML to defend privacy leakage.

Random feature mapping (RFM) is a popular method for speeding up kernel methods at the cost of losing a little accuracy. We study kernel ridge regression with random feature mapping (RFM-KRR) and establish novel out-of-sample error upper and lower bounds. While out-of-sample bounds for RFM-KRR have been established by prior work, this paper's theories are highly interesting for two reasons. On the one hand, our theories are based on weak and valid assumptions. In contrast, the existing theories are based on various uncheckable assumptions, which makes it unclear whether their bounds are the nature of RFM-KRR or simply the consequence of strong assumptions. On the other hand, our analysis is completely based on elementary linear algebra and thereby easy to read and verify. Finally, our experiments lend empirical supports to the theories.