The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the conventional training framework for reward models that directly optimizes the predicted rewards. In this paper, we propose a hybrid alignment framework HaF-RM for reward model training by introducing an additional constraint on token-level policy probabilities in addition to the reward score. It can simultaneously supervise the internal preference model at the token level and optimize the mapping layer of the reward model at the sequence level. Theoretical justifications and experiment results on five datasets show the validity and effectiveness of our proposed hybrid framework for training a high-quality reward model. By decoupling the reward modeling procedure and incorporating hybrid supervision, our HaF-RM framework offers a principled and effective approach to enhancing the performance and alignment of reward models, a critical component in the responsible development of powerful language models. We release our code at https://haf-rm.github.io.

The problem of finite/fixed-time cooperative state estimation is considered for a class of quasilinear systems with nonlinearities satisfying a H\"older condition. A strongly connected nonlinear distributed observer is designed under the assumption of global observability. By proper parameter tuning with linear matrix inequalities, the observer error equation possesses finite/fixed-time stability in the perturbation-free case and input-to-state stability with respect to bounded perturbations. Numerical simulations are performed to validate this design.

The rapid development of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has exposed vulnerabilities to various adversarial attacks. This paper provides a comprehensive overview of jailbreaking research targeting both LLMs and MLLMs, highlighting recent advancements in evaluation benchmarks, attack techniques and defense strategies. Compared to the more advanced state of unimodal jailbreaking, multimodal domain remains underexplored. We summarize the limitations and potential research directions of multimodal jailbreaking, aiming to inspire future research and further enhance the robustness and security of MLLMs.

Large language models (LLMs) have achieved impressive human-like performance across various reasoning tasks. However, their mastery of underlying inferential rules still falls short of human capabilities. To investigate this, we propose a logic scaffolding inferential rule generation framework, to construct an inferential rule base, ULogic, comprising both primitive and compositional rules across five domains. Our analysis of GPT-series models over a rule subset reveals significant gaps in LLMs' logic understanding compared to human performance, especially in compositional and structural complex rules with certain bias patterns. We further distill these rules into a smaller-scale inference engine for flexible rule generation and enhancing downstream reasoning. Through a multi-judger evaluation, our inference engine proves effective in generating accurate, complex and abstract conclusions and premises, and improve various commonsense reasoning tasks. Overall, our work sheds light on LLMs' limitations in grasping inferential rule and suggests ways to enhance their logical reasoning abilities~\footnote{Code and data are available at \url{https://github.com/SiyuanWangw/ULogic}.}.

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework addresses the limitations of current alignment approaches, which often struggle with the inconsistency and sparsity of human supervision signals, by integrating holistic rewards with aspect-specific rewards. This integration enables more precise and consistent guidance of language models towards desired outcomes, particularly in complex and open text generation tasks. By employing a methodology that filters and combines multiple rewards based on their consistency, the framework provides a reliable mechanism for improving model alignment. We validate our approach through applications in long-form question answering and machine translation tasks, employing gpt-3.5-turbo for pairwise comparisons, and demonstrate improvements over existing baselines. Our work underscores the effectiveness of hierarchical rewards modeling in refining LLM training processes for better human preference alignment. We release our code at https://ALaRM-fdu.github.io.

Graph Databases (Graph DB) are widely applied in various fields, including finance, social networks, and medicine. However, translating Natural Language (NL) into the Graph Query Language (GQL), commonly known as NL2GQL, proves to be challenging due to its inherent complexity and specialized nature. Some approaches have sought to utilize Large Language Models (LLMs) to address analogous tasks like text2SQL. Nevertheless, when it comes to NL2GQL taskson a particular domain, the absence of domain-specific NL-GQL data pairs makes it difficult to establish alignment between LLMs and the graph DB. To address this challenge, we propose a well-defined pipeline. Specifically, we utilize ChatGPT to create NL-GQL data pairs based on the given graph DB with self-instruct. Then, we use the created data to fine-tune LLMs, thereby achieving alignment between LLMs and the graph DB. Additionally, during inference, we propose a method that extracts relevant schema to the queried NL as the input context to guide LLMs for generating accurate GQLs.We evaluate our method on two constructed datasets deriving from graph DBs in finance domain and medicine domain, namely FinGQL and MediGQL. Experimental results demonstrate that our method significantly outperforms a set of baseline methods, with improvements of 5.90 and 6.36 absolute points on EM, and 6.00 and 7.09 absolute points on EX, respectively.

In recent years, the recognition of free-hand sketches has remained a popular task. However, in some special fields such as the military field, free-hand sketches are difficult to sample on a large scale. Common data augmentation and image generation techniques are difficult to produce images with various free-hand sketching styles. Therefore, the recognition and segmentation tasks in related fields are limited. In this paper, we propose a novel adversarial generative network that can accurately generate realistic free-hand sketches with various styles. We explore the performance of the model, including using styles randomly sampled from a prior normal distribution to generate images with various free-hand sketching styles, disentangling the painters' styles from known free-hand sketches to generate images with specific styles, and generating images of unknown classes that are not in the training set. We further demonstrate with qualitative and quantitative evaluations our advantages in visual quality, content accuracy, and style imitation on SketchIME.

With the recent surge in the use of touchscreen devices, free-hand sketching has emerged as a promising modality for human-computer interaction. While previous research has focused on tasks such as recognition, retrieval, and generation of familiar everyday objects, this study aims to create a Sketch Input Method Editor (SketchIME) specifically designed for a professional C4I system. Within this system, sketches are utilized as low-fidelity prototypes for recommending standardized symbols in the creation of comprehensive situation maps. This paper also presents a systematic dataset comprising 374 specialized sketch types, and proposes a simultaneous recognition and segmentation architecture with multilevel supervision between recognition and segmentation to improve performance and enhance interpretability. By incorporating few-shot domain adaptation and class-incremental learning, the network's ability to adapt to new users and extend to new task-specific classes is significantly enhanced. Results from experiments conducted on both the proposed dataset and the SPG dataset illustrate the superior performance of the proposed architecture. Our dataset and code are publicly available at https://github.com/Anony517/SketchIME.

Since large language models have approached human-level performance on many tasks, it has become increasingly harder for researchers to find tasks that are still challenging to the models. Failure cases usually come from the long-tail distribution - data that an oracle language model could assign a probability on the lower end of its distribution. Current methodology such as prompt engineering or crowdsourcing are insufficient for creating long-tail examples because humans are constrained by cognitive bias. We propose a Logic-Induced-Knowledge-Search (LINK) framework for systematically generating long-tail knowledge statements. Grounded by a symbolic rule, we search for long-tail values for each variable of the rule by first prompting a LLM, then verifying the correctness of the values with a critic, and lastly pushing for the long-tail distribution with a reranker. With this framework we construct a dataset, Logic-Induced-Long-Tail (LINT), consisting of 200 symbolic rules and 50K knowledge statements spanning across four domains. Human annotations find that 84% of the statements in LINT are factually correct. In contrast, ChatGPT and GPT4 struggle with directly generating long-tail statements under the guidance of logic rules, each only getting 56% and 78% of their statements correct. Moreover, their "long-tail" generations in fact fall into the higher likelihood range, and thus are not really long-tail. Our findings suggest that LINK is effective for generating data in the long-tail distribution while enforcing quality. LINT can be useful for systematically evaluating LLMs' capabilities in the long-tail distribution. We challenge the models with a simple entailment classification task using samples from LINT. We find that ChatGPT and GPT4's capability in identifying incorrect knowledge drop by ~3% in the long-tail distribution compared to head distribution.

The financial industry presents unique challenges and opportunities for Natural Language Processing In this paper, we propose a comprehensive approach (NLP) models (Huang et al., 2020). Traditional to build Chinese financial LLMs and present financial NLP models have made progress DISC-FinLLM. Our method aims to enhance general in various tasks such as news sentiment analysis LLMs by equipping them with the skills to (Araci, 2019), financial event extraction (Zheng address typical needs for financial text generation et al., 2019; Yang et al., 2019), financial report and understanding, meaningful multi-turn conversations generation (Chapman et al., 2022), stock price prediction on financial topics, and plugin functionality (Chen et al., 2018) and financial text summarization to support financial modeling and knowledgeenhanced (La Quatra and Cagliero, 2020).