Automatic speech recognition (ASR) systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0 and HuBERT. However, developing robust ASR models for young children’s speech remains challenging due to differences in pronunciation, tone, and pace compared to adult speech. In this paper, we introduce a new Mandarin speech dataset focused on children aged 3 to 5, addressing the scarcity of resources in this area. The dataset comprises 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation. We provide a comprehensive analysis of speaker demographics, speech duration distribution and geographic coverage. Additionally, we evaluate ASR performance on models trained from scratch, such as Conformer, as well as fine-tuned pre-trained models like HuBERT and Whisper, where fine-tuning demonstrates significant performance improvements. Furthermore, we assess speaker verification (SV) on our dataset, showing that, despite the challenges posed by the unique vocal characteristics of young children, the dataset effectively supports both ASR and SV tasks. This dataset is a valuable contribution to Mandarin child speech research and holds potential for applications in educational technology and child-computer interaction. It will be open-source and freely available for all academic purposes.

Tool invocation significantly enhances the capabilities of Large Language Models (LLMs), yet challenges persist, particularly in complex task scenarios. Current methods, such as instruction-enhanced reasoning and supervised fine-tuning, often result in unnecessarily long reasoning paths and face difficulties in verifying the correctness of intermediate steps. In this paper, we propose CodeTool, a novel framework for stepwise code generation that improves LLM tool invocation by leveraging the concise and easily verifiable nature of code. CodeTool incorporates two distinct process rewards: the On-the-spot Reward, which provides immediate feedback on the accuracy of each tool invocation, and the Latent Reward, which assesses the contribution of each step toward overall task completion. By maximizing the cumulative reward of the On-the-spot and Latend Rewards at each step, LLMs are guided to follow efficient and accurate reasoning paths. Extensive experiments on StableToolBench and RestBench-TMDB demonstrate the superiority of CodeTool over existing approaches.

Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs’ deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less powerful base models. In this work, we introduce S²R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Specifically, we first initialize LLMs with iterative self-verification and self-correction behaviors through supervised fine-tuning on carefully curated data. The self-verification and self-correction skills are then further strengthened by outcome-level and process-level reinforcement learning with minimized resource requirements. Our results demonstrate that, with only 3.1k behavior initialization samples, Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data. We also discuss the effect of different RL strategies on enhancing LLMs’ deep reasoning. Extensive experiments and analysis based on three base models across both in-domain and out-of-domain benchmarks validate the effectiveness of S²R.

Event Causality Identification (ECI) aims to detect whether there exists a causal relation between two events in a document. Existing studies adopt a kind of *identifying after learning* paradigm, where events’ representations are first learned and then used for the identification. Furthermore, they mainly focus on the causality existence, but ignoring causal direction. In this paper, we take care of the causal direction and propose a new *identifying while learning* mode for the ECI task. We argue that a few causal relations can be easily identified with high confidence, and the directionality and structure of these identified causalities can be utilized to update events’ representations for boosting next round of causality identification. To this end, this paper designs an *iterative learning and identifying framework*: In each iteration, we construct an event causality graph, on which events’ causal structure representations are updated for boosting causal identification. Experiments on two public datasets show that our approach outperforms the state-of-the-art algorithms in both evaluations for causality existence identification and direction identification.

Recently, fine-tuning the large pre-trained language models on the labeled sentiment dataset achieves appealing performance. However, the obtained model may not generalize well to the other domains due to the domain shift, and it is expensive to update the entire parameters within the large models. Although some existing domain matching methods are proposed to alleviate the above issues, there are multiple relevant source domains in practice which makes the whole training more costly and complicated. To this end, we focus on the efficient unsupervised multi-source sentiment adaptation task which is more challenging and beneficial for real-world applications. Specifically, we propose to extract multi-layer features from the large pre-trained model, and design a dynamic parameters fusion module to exploit these features for both efficient and adaptive tuning. Furthermore, we propose a novel feature structure matching constraint, which enforces similar feature-wise correlations across different domains. Compared with the traditional domain matching methods which tend to pull all feature instances close, we show that the proposed feature structure matching is more robust and generalizable in the multi-source scenario. Extensive experiments on several multi-source sentiment analysis benchmarks demonstrate the effectiveness and superiority of our proposed framework.

Recently, fine-tuning the pre-trained language model (PrLM) on labeled sentiment datasets demonstrates impressive performance. However, collecting labeled sentiment dataset is time-consuming, and fine-tuning the whole PrLM brings about much computation cost. To this end, we focus on multi-source unsupervised sentiment adaptation problem with the pre-trained features, which is more practical and challenging. We first design a dynamic feature network to fully exploit the extracted pre-trained features for efficient domain adaptation. Meanwhile, with the difference of the traditional source-target domain alignment methods, we propose a novel asymmetric mutual learning strategy, which can robustly estimate the pseudo-labels of the target domain with the knowledge from all the other source models. Experiments on multiple sentiment benchmarks show that our method outperforms the recent state-of-the-art approaches, and we also conduct extensive ablation studies to verify the effectiveness of each the proposed module.