Search

Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive in reasoning tasks due to LLMs' difficulties in identifying logical mistakes. In this paper, we aim to enhance the self-checking capabilities of LLMs by constructing training data for checking tasks. Specifically, we apply the Chain of Thought (CoT) methodology to self-checking tasks, utilizing fine-grained step-level analyses and explanations to assess the correctness of reasoning paths. We propose a specialized checking format called "Step CoT Check". Following this format, we construct a checking-correction dataset that includes detailed step-by-step analysis and checking. Then we fine-tune LLMs to enhance their error detection and correction abilities. Our experiments demonstrate that fine-tuning with the "Step CoT Check" format significantly improves the self-checking and self-correction abilities of LLMs across multiple benchmarks. This approach outperforms other formats, especially in locating the incorrect position, with greater benefits observed in larger models. For reproducibility, all the datasets and code are provided in https://github.com/bammt/Learn-to-check.

Chain-of-Thought (CoT) prompting has proven to be effective in enhancing the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters. However, it is ineffective or even detrimental when applied to reasoning tasks in Smaller Language Models (SLMs) with less than 10 billion parameters. To address this limitation, we introduce Dialogue-guided Chain-of-Thought (DialCoT) which employs a dialogue format to generate intermediate reasoning steps, guiding the model toward the final answer. Additionally, we optimize the model's reasoning path selection using the Proximal Policy Optimization (PPO) algorithm, further enhancing its reasoning capabilities. Our method offers several advantages compared to previous approaches. Firstly, we transform the process of solving complex reasoning questions by breaking them down into a series of simpler sub-questions, significantly reducing the task difficulty and making it more suitable for SLMs. Secondly, we optimize the model's reasoning path selection through the PPO algorithm. We conduct comprehensive experiments on four arithmetic reasoning datasets, demonstrating that our method achieves significant performance improvements compared to state-of-the-art competitors., Comment: Accepted to EMNLP 2023

The study of human values is essential in both practical and theoretical domains. With the development of computational linguistics, the creation of large-scale datasets has made it possible to automatically recognize human values accurately. SemEval 2023 Task 4\cite{kiesel:2023} provides a set of arguments and 20 types of human values that are implicitly expressed in each argument. In this paper, we present our team's solution. We use the Roberta\cite{liu_roberta_2019} model to obtain the word vector encoding of the document and propose a multi-head attention mechanism to establish connections between specific labels and semantic components. Furthermore, we use a contrastive learning-enhanced K-nearest neighbor mechanism\cite{su_contrastive_2022} to leverage existing instance information for prediction. Our approach achieved an F1 score of 0.533 on the test set and ranked fourth on the leaderboard.

Link failures and cable miswirings are not uncommon in building data center networks, which prevents the existing automatic address configuration methods from functioning correctly. However, accurately detecting such malfunctions is not an easy task because there could be no observable node degree changes. Fixing or correcting such malfunctions is even harder as almost no work can provide accurate fixation suggestions now. To solve the problems, we design and implement A3, an automatic topology-aware malfunction detection and fixation system. A3 innovatively formulates the problem of finding minimal fixation to the problem of computing minimum graph difference (NP-hard) and solves it in O(k^6) and O(k^3) for any less than k/2 and k/4 undirected link malfunctions for FatTree, respectively. Our evaluation demonstrates that for less than k/2 undirected link malfunctions, A3 is 100% accurate for malfunction detection and provides the minimum fixation result. For greater or equal to k/2 undirected link malfunctions, A3 still has accuracy of about 100% and provides the near optimal fixation result., Comment: The poster version is published as a SIGCOMM 2019 poster, and the 5 pages' version is under submission

Existing traffic engineering (TE) solutions performs well for software defined network (SDN) in average cases. However, during peak hours, bursty traffic spikes are challenging to handle, because it is difficult to react in time and guarantee high performance even after failures with limited flow entries. Instead of leaving some capacity empty to guarantee no congestion happens due to traffic rerouting after failures or path updating after demand or topology changes, we decide to make full use of the network capacity to satisfy the demands for heavily-loaded peak hours. The TE system also needs to react to failures quickly and utilize the priority queue to guarantee the transmission of loss and delay sensitive traffic. We propose TED, a scalable TE system that can guarantee high throughput in peak hours. TED can quickly compute a group of maximum number of edge-disjoint paths for each ingress-egress switch pair. We design two methods to select paths under the flow entry limit. We then input the selected paths to our TE to minimize the maximum link utilization. In case of large traffic matrix making the maximum link utilization larger than 1, we input the utilization and the traffic matrix to the optimization of maximizing overall throughput under a new constrain. Thus we obtain a realistic traffic matrix, which has the maximum overall throughput and guarantees no traffic starvation for each switch pair. Experiments show that TED has much better performance for heavily-loaded SDN and has 10% higher probability to satisfy all (> 99.99%) the traffic after a single link failure for G-Scale topology than Smore under the same flow entry limit., Comment: The 8 pages double column version of the paper is submitted to NOMS 2020 technical session