Reasoning capability plays a significantly critical role in the the broad applications of Large Language Models (LLMs).To enhance the reasoning performance of LLMs, diverse Reinforcement Learning (RL)-based fine-tuning approaches have been proposed to address the limited generalization capability of LLMs trained solely via Supervised Fine-Tuning (SFT).Despite their effectiveness, two major limitations hinder the advancement of LLMs.First, vanilla RL-based approaches ignore annotated Chainof-Thought (CoT) and incorporate unstable reasoning path sampling, which typically results in model collapse, unstable training process, and suboptimal performance.Second, existing SFT approaches generally overemphasize the annotated CoT, potentially leading to performance degradation due to insufficient exploitation of potential CoT.In this paper, we propose a Contrastive learning with annotated CoT-based Reinforced Fine-Tuning approach, i.e., CARFT, to enhance the reasoning performance of LLMs while addressing the aforementioned limitations.Specifically, we propose learning a representation for each CoT.Based on this representation, we design novel contrastive signals to guide the fine-tuning process.Our approach not only fully exploits the available annotated CoT but also stabilizes the finetuning procedure by incorporating an additional unsupervised learning signal.We conduct comprehensive experiments and in-depth analysis with three baseline approaches, two foundation models, and two datasets to demonstrate significant advantages of CARFT in terms of robustness, performance (up to 10.15%), and efficiency (up to 30.62%).Code is available at https://github.com/WNQzhu/CARFT.

Human beings perceive the real world through a spectrum of sensory modalities, encompassing auditory, visual, and linguistic faculties. This work proposes an industry-level omni-modal large language model (LLM) pipeline that integrates auditory, visual, and linguistic modalities to overcome challenges such as limited tri-modal datasets, high computational costs, and complex feature alignments. Our pipeline consists of three main components: First, a modular, end-to-end framework enabling flexible configuration of various encoder-LLM-decoder architectures. Second, a lightweight training strategy that pre-trains audio-language alignment on the state-of-the-art vision-language model Qwen2.5-VL, thus avoiding the costly pre-training of vision-specific modalities. Third, an audio synthesis pipeline that generates high-quality audio-text data from diverse real-world scenarios, supporting applications such as Automatic Speech Recognition and Speech-to-Speech chat. To this end, we introduce an industry-level omni-modal LLM, NEXUS-O. Extensive experiments validate the efficacy of our pipeline, yielding the following key findings: (1) In the visual understanding task, NEXUSO exhibits superior performance compared with its backbone model - Qwen2.5-VL-7B, validating the efficiency of our training strategy. (2) Within the English Spoken Question-Answering task, the model achieves better accuracy than the same-period competitor (i.e, MiniCPM-o2.6-7B) in the LLaMA Q. benchmark. (3) In our realworld ASR testset, NEXUS-O achieves outstanding performance, indicating its robustness in real scenarios. (4) In the Speech-to-Text Translation task, our model outperforms Qwen2-Audio-Instruct-7B. (5) In the Text-to-Speech task, based on pretrained vocoder (e.g., Fishspeech1.4 or CosyVoice2.0), NEXUS-O is comparable to its backbone vocoder on Seed-TTS benchmark. (6) An in-depth analysis of tri-modal alignment reveals that incorporating the audio modality enhances representational alignment between vision and language.

To date, there is a notable lack of rigorous benchmarks that assess Multimodal Large Language Models (MLLMs) within the financial domain, a field characterized by specialized financial charts and complex domain-specific expertise. To address this gap, we introduce MME-Finance, the first comprehensive bilingual multimodal benchmark tailored for financial analysis. MME-Finance comprises 4,751 meticulously curated samples, encompassing 2,274 open-ended questions, 2,000 binary-choice questions, and 477 multi-turn questions. To mitigate bias when LLMs act as judges, we also created an evaluation framework that strengthens alignment with human judgments by embedding visual context into the multimodal assessment pipeline. A comprehensive evaluation of 31 popular MLLMs has been conducted to assess their perception, reasoning, and cognitive capabilities. Gemini2.5Pro achieves highest accuracy of 79.28% and 85.71% on the open-ended questions and multi-turn questions, respectively. Among open-source models, InternVL3-78B attains 71.24 % accuracy on the open-ended question, whereas Qwen2.5-VL-72B achieves an F1 score of 88.73 % on the binary-choice question. The results indicate that state-of-the-art MLLMs demonstrate considerable overall competence, yet exhibit significant deficiencies in fine-grained visual perception and the understanding of domain-specific financial images. Source code is available at https://github.com/HiThink-Research/MME-Finance.

Businesses face a range of cyber risks, both external threats and internal vulnerabilities that continue to evolve over time. As cyber attacks continue to increase in complexity and sophistication, more organisations will experience them. For this reason, it is important that organisations seek timely consultancy from cyber professionals so that they can respond to and recover from cyber attacks as quickly as possible. However, huge surges in cyber attacks have long left cyber professionals short of what is required to cover the security needs. This problem is getting worse when an increasing number of people choose to work from home during the pandemic because this situation usually yields extra communication cost.

Multi-turn response selection is a key issue in retrieval-based chatbots and has attracted considerable attention in the NLP (Natural Language processing) field. So far, researchers have developed many solutions that can select appropriate responses for multi-turn conversations. However, these works are still suffering from the semantic mismatch problem when responses and context share similar words with different meanings. In this article, we propose a novel chatbot model based on Semantic Awareness Matching, called SAM. SAM can capture both similarity and semantic features in the context by a two-layer matching network. Appropriate responses are selected according to the matching probability made through the aggregation of the two feature types. In the evaluation, we pick 4 widely used datasets and compare SAM’s performance to that of 12 other models. Experiment results show that SAM achieves substantial improvements, with up to 1.5% R 10 @1 on Ubuntu Dialogue Corpus V2, 0.5% R 10 @1 on Douban Conversation Corpus, and 1.3% R 10 @1 on E-commerce Corpus.

Users receive a multitude of security information in written articles, e.g., newspapers, security blogs, and training materials. However, prior research suggests that these delivery methods, including security awareness campaigns, mostly fail to increase people's knowledge about cyber threats. It seems that users find such information challenging to absorb and understand. Yet, to raise users' security awareness and understanding, it is essential to ensure the users comprehend the provided information so that they can apply the advice it contains in practice. We conducted a subjective study to measure the level of users' understanding of security texts. We find that 61% of the terms security experts used in their writings are hard for the public to understand, even for people with some IT backgrounds. We also observe that 88% of security texts have at least one such term. Moreover, we notice that existing dictionaries, including the online ones (e.g., Google Dictionary), cover no more than 35% of the terms found in security texts. To improve users' ability to understand security texts, we developed a framework to build a user-oriented security-centric dictionary from multiple sources. To evaluate the effectiveness of the dictionary, we developed a tool as a service to detect technical terms and explain their meanings to the user in pop-ups. The results of a subjective study to measure the tool's performance showed that it could increase users' ability to understand security articles by 30%.

Android users are increasingly concerned with the privacy of their data and security of their devices. To improve the security awareness of users, recent automatic techniques produce security-centric descriptions by performing program analysis. However, the generated text does not always address users’ concerns as they are generally too technical to be understood by ordinary users. Moreover, different users have varied linguistic preferences that do not match the text. Motivated by this challenge, we develop an innovative scheme to help users avoid malware and privacy-breaching apps by generating security descriptions that explain the privacy and security related aspects of an Android app in clear and understandable terms. We implement a prototype system, PERSCRIPTION, to generate personalised security-centric descriptions that automatically learn users’ security concerns and linguistic preferences to produce user-oriented descriptions. We evaluate our scheme through experiments and user studies. The results clearly demonstrate the improvement on readability and users’ security awareness of PERSCRIPTION’s descriptions compared to existing description generators.