ALaRM: Align Language Models via Hierarchical Rewards Modeling

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.

Aligning Large Language Models to a Domain-specific Graph Database

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.

AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis

The incorporation of Large Language Models (LLMs) in healthcare marks a significant advancement. However, the application has predominantly been limited to discriminative and question-answering tasks, which does not fully leverage their interactive potential. To address this limitation, our paper presents AI Hospital, a framework designed to build a real-time interactive diagnosis environment. To simulate the procedure, we collect high-quality medical records to create patient, examiner, and medical director agents. AI Hospital is then utilized for the interactive evaluation and collaboration of LLMs. Initially, we create a Multi-View Medical Evaluation (MVME) benchmark where various LLMs serve as intern doctors for interactive diagnosis. Subsequently, to improve diagnostic accuracy, we introduce a collaborative mechanism that involves iterative discussions and a dispute resolution process under the supervision of the medical director. In our experiments, we validate the reliability of AI Hospital. The results not only explore the feasibility of apply LLMs in clinical consultation but also confirm the effectiveness of the dispute resolution focused collaboration method.

Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation

This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs), aiming for a more accurate assessment of their capabilities and limitations. We utilize a multi-agent system to manipulate the context or question of original instances, reframing new evolving instances with high confidence that dynamically extend existing benchmarks. Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, data noise and probing their problem-solving sub-abilities. With this framework, we extend benchmark datasets of four tasks. Experimental results show a general performance decline in most LLMs against their original results. This decline under our scalable and robust evaluations, alongside our fine-grained evaluation, more accurately reflect models' capabilities. Besides, our framework widens performance discrepancies both between different models and within the same model across various tasks, facilitating more informed model selection for specific tasks (Code and data are available at https://github.com/NanshineLoong/Self-Evolving-Benchmark).

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs

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}.}.

Content-Conditioned Generation of Stylized Free hand Sketches

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.

Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion Approach

Flowcharts and mind maps, collectively known as flowmind, are vital in daily activities, with hand-drawn versions facilitating real-time collaboration. However, there's a growing need to digitize them for efficient processing. Automated conversion methods are essential to overcome manual conversion challenges. Existing sketch recognition methods face limitations in practical situations, being field-specific and lacking digital conversion steps. Our paper introduces the Flowmind2digital method and hdFlowmind dataset to address these challenges. Flowmind2digital, utilizing neural networks and keypoint detection, achieves a record 87.3% accuracy on our dataset, surpassing previous methods by 11.9%. The hdFlowmind dataset, comprising 1,776 annotated flowminds across 22 scenarios, outperforms existing datasets. Additionally, our experiments emphasize the importance of simple graphics, enhancing accuracy by 9.3%.

Diff-Oracle: Diffusion Model for Oracle Character Generation with Controllable Styles and Contents

Deciphering the oracle bone script plays a significant role in Chinese archaeology and philology. However, it is significantly challenging due to the scarcity of oracle character images. To overcome this issue, we propose Diff-Oracle, based on diffusion models (DMs), to generate sufficient controllable oracle characters. In contrast to most DMs that rely on text prompts, we incorporate a style encoder to control style information during the generation process. This encoder extracts style prompts from existing oracle character images, where style details are converted from a CLIP model into a text embedding format. Inspired by ControlNet, we introduce a content encoder to capture desired content information from content images, ensuring the fidelity of character glyphs. To train Diff-Oracle effectively, we propose to obtain pixel-level paired oracle character images (i.e., style and content images) by a pre-trained image-to-image translation model. Extensive qualitative and quantitative experiments conducted on two benchmark datasets, Oracle-241 and OBC306, demonstrate that our Diff-Oracle outperforms existing generative methods in terms of image generation, further enhancing recognition accuracy. Source codes will be available.