Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if they initially provided the correct answer. Recent works propose to employ supervised fine-tuning (SFT) to mitigate the sycophancy issue, while it typically leads to the degeneration of LLMs' general capability. To address the challenge, we propose a novel supervised pinpoint tuning (SPT), where the region-of-interest modules are tuned for a given objective. Specifically, SPT first reveals and verifies a small percentage (<5%) of the basic modules, which significantly affect a particular behavior of LLMs. i.e., sycophancy. Subsequently, SPT merely fine-tunes these identified modules while freezing the rest. To verify the effectiveness of the proposed SPT, we conduct comprehensive experiments, demonstrating that SPT significantly mitigates the sycophancy issue of LLMs (even better than SFT). Moreover, SPT introduces limited or even no side effects on the general capability of LLMs. Our results shed light on how to precisely, effectively, and efficiently explain and improve the targeted ability of LLMs.

While features of different scales are perceptually important to visual inputs, existing vision transformers do not yet take advantage of them explicitly. To this end, we first propose a cross-scale vision transformer, CrossFormer. It introduces a cross-scale embedding layer (CEL) and a long-short distance attention (LSDA). On the one hand, CEL blends each token with multiple patches of different scales, providing the self-attention module itself with cross-scale features. On the other hand, LSDA splits the self-attention module into a short-distance one and a long-distance counterpart, which not only reduces the computational burden but also keeps both small-scale and large-scale features in the tokens. Moreover, through experiments on CrossFormer, we observe another two issues that affect vision transformers' performance, i.e., the enlarging self-attention maps and amplitude explosion. Thus, we further propose a progressive group size (PGS) paradigm and an amplitude cooling layer (ACL) to alleviate the two issues, respectively. The CrossFormer incorporating with PGS and ACL is called CrossFormer++. Extensive experiments show that CrossFormer++ outperforms the other vision transformers on image classification, object detection, instance segmentation, and semantic segmentation tasks.

The phenomenon of propagation is universal in our daily life. For example, infectious diseases can be transmitted from one person to another, hot news is disseminated widely on the Internet, and classic passages written by the popular users can be shared by many other users in online social network sites. With the emerging of online social network sites, such as Facebook, YouTube, and Flickr, many literatures try to analyse patterns of information propagation and design effective virtual marketing strategies in these sites. However, few metrics have been designed to measure the characteristic of information propagation. In this paper, we propose a novel metric for measuring members’ contribution to information propagation in online social network sites. As a case, we analyse large-scale traces of members’ contribution to photo dissemination in Flickr and find that the distribution of members’ contribution follows a power law distribution, which reveals that most of the information is created and propagated by a few members.

Online monitoring of temporally-sequenced news streams for interesting patterns and trends has gained popularity in the last decade. In this paper, we study a particular news stream monitoring task: timely detection of bursty events which have happened recently and discovery of their evolutionary patterns along the timeline. Here, a news stream is represented as feature streams of tens of thousands of features (i.e., keyword. Each news story consists of a set of keywords.). A bursty event therefore is composed of a group of bursty features, which show bursty rises in frequency as the related event emerges. In this paper, we give a formal definition to the above problem and present a solution with the following steps: (1) applying an online multi-resolution burst detection method to identify bursty features with different bursty durations within a recent time period; (2) clustering bursty features to form bursty events and associating each event with a power value which reflects its bursty level; (3) applying an information retrieval method based on cosine similarity to discover the event’s evolution (i.e., highly related bursty events in history) along the timeline. We extensively evaluate the proposed methods on the Reuters Corpus Volume 1. Experimental results show that our methods can detect bursty events in a timely way and effectively discover their evolution. The power values used in our model not only measure event’s bursty level or relative importance well at a certain time point but also show relative strengths of events along the same evolution.

Content Based Image Retrieval (CBIR) has become one of the most active research areas in computer science. Relevance feedback is often used in CBIR systems to bridge the semantic gap. Typically, users are asked to make relevance judgements on some query results, and the feedback information is then used to re-rank the images in the database. An effective relevance feedback algorithm must provide the users with the most informative images with respect to the ranking function. In this paper, we propose a novel active learning algorithm, called Convex Laplacian Regularized I-optimal Design (CLapRID), for relevance feedback image retrieval. Our algorithm is based on a regression model which minimizes the least square error on the labeled images and simultaneously preserves the intrinsic geometrical structure of the image space. It selects the most informative images which minimize the average predictive variance. The optimization problem of CLapRID can be cast as a semidefinite programming (SDP) problem, and solved via interior-point methods. Experimental results on COREL database have demonstrate the effectiveness of the proposed algorithm for relevance feedback image retrieval. Categories and Subject Descriptors H.3.3 [Information storage and retrieval]: Information search and retrieval—Relevance feedback; G.3 [Mathematics of Computing]: Probability and Statistics—Experimental design

No abstract available.

This paper makes an intensive investigation of the application of Bayesian network in sentence retrieval and introduces three Bayesian network based sentence retrieval models with or without consideration of term relationships. Term relationships in this paper are considered from two perspectives: relationships between pairs of terms and relationships between terms and term sets. Experiments have proven the efficiency of Bayesian network in the application of sentence retrieval. Particularly, retrieval result with consideration of the second kind of term relationship performs better in improving retrieval precision.

There has been a rapid growth in the amount and the importance of software in automobiles in the past two decades. This trend makes us view automobile space as a set of smart services. The basic platform for managing these services is a real-time operating system. Due to the limited resource in ECU, this operating system must be efficient in some aspects especially in memory utilization. We have implemented an operating system SmartOSEK, an OSEK-compliant OS. Some features and optimizations to reduce the RAM needed by the operating system are presented in this paper. First, an upper bound for the register set of each task that has to be stored can be calculated off-line. It also calls for the extension of the compiler to allocate registers across tasks for task contexts. We provide an experimental implementation with its result shown in this paper. Second, the stack space is saved based on some properties of tasks and interrupt handling.