How to better evaluate the capabilities of Large Language Models (LLMs) is the focal point and hot topic in current LLMs research. Previous work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer the latest dynamic questions well. To promote the improvement of Chinese LLMs' ability to answer dynamic questions, in this paper, we introduce CDQA, a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest news on the Chinese Internet. We obtain high-quality data through a pipeline that combines humans and models, and carefully classify the samples according to the frequency of answer changes to facilitate a more fine-grained observation of LLMs' capabilities. We have also evaluated and analyzed mainstream and advanced Chinese LLMs on CDQA. Extensive experiments and valuable insights suggest that our proposed CDQA is challenging and worthy of more further study. We believe that the benchmark we provide will become one of the key data resources for improving LLMs' Chinese question-answering ability in the future.

Spoken Question Answering (QA) is a key feature of voice assistants, usually backed by multiple QA systems. Users ask questions via spontaneous speech which can contain disfluencies, errors, and informal syntax or phrasing. This is a major challenge in QA, causing unanswered questions or irrelevant answers, and leading to bad user experiences. We analyze failed QA requests to identify core challenges: lexical gaps, proposition types, complex syntactic structure, and high specificity. We propose a Semantic Question Reformulation (SURF) model offering three linguistically-grounded operations (repair, syntactic reshaping, generalization) to rewrite questions to facilitate answering. Offline evaluation on 1M unanswered questions from a leading voice assistant shows that SURF significantly improves answer rates: up to 24% of previously unanswered questions obtain relevant answers (75%). Live deployment shows positive impact for millions of customers with unanswered questions; explicit relevance feedback shows high user satisfaction.

LogAnswer is a question answering (QA) system for the German language, aimed at providing concise and correct answers to arbitrary questions. For this purpose LogAnswer is designed as an embedded artificial intelligence system which integrates methods from several fields of AI, namely natural language processing, machine learning, knowledge representation and automated theorem proving. We intend to employ LogAnswer as a virtual user within Internet-based QA forums, where it must be able to identify the questions that it cannot answer correctly, a task that normally receives little attention in QA research compared to the actual answer derivation. The paper presents a machine learning solution to the wrong answer avoidance (WAA) problem, applying a meta classifier to the output of simple term-based classifiers and a rich set of other WAA features. Experiments with a large set of real-world questions from a QA forum show that the proposed method significantly improves the WAA characteristics of our system.