SimPO: Simple Preference Optimization with a Reference-Free Reward

Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback (RLHF) to enhance simplicity and training stability. In this work, we propose SimPO, a simpler yet more effective approach. The effectiveness of SimPO is attributed to a key design: using the average log probability of a sequence as the implicit reward. This reward formulation better aligns with model generation and eliminates the need for a reference model, making it more compute and memory efficient. Additionally, we introduce a target reward margin to the Bradley-Terry objective to encourage a larger margin between the winning and losing responses, further enhancing the algorithm's performance. We compare SimPO to DPO and its latest variants across various state-of-the-art training setups, including both base and instruction-tuned models like Mistral and Llama3. We evaluated on extensive instruction-following benchmarks, including AlpacaEval 2, MT-Bench, and the recent challenging Arena-Hard benchmark. Our results demonstrate that SimPO consistently and significantly outperforms existing approaches without substantially increasing response length. Specifically, SimPO outperforms DPO by up to 6.4 points on AlpacaEval 2 and by up to 7.5 points on Arena-Hard. Our top-performing model, built on Llama3-8B-Instruct, achieves a remarkable 44.7 length-controlled win rate on AlpacaEval 2 -- surpassing Claude 3 Opus on the leaderboard, and a 33.8 win rate on Arena-Hard -- making it the strongest 8B open-source model.

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs

Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, texts are interconnected (e.g., academic papers in a bibliographic graph are linked by citations and co-authorships) which form a (text-attributed) graph. The knowledge in such graphs is encoded not only in single texts/nodes but also in their associated connections. To facilitate the research of augmenting LLMs with graphs, we manually construct a Graph Reasoning Benchmark dataset called GRBench, containing 1,740 questions that can be answered with the knowledge from 10 domain graphs. Then, we propose a simple and effective framework called Graph Chain-of-thought (Graph-CoT) to augment LLMs with graphs by encouraging LLMs to reason on the graph iteratively. Each Graph-CoT iteration consists of three sub-steps: LLM reasoning, LLM-graph interaction, and graph execution. We conduct systematic experiments with three LLM backbones on GRBench, where Graph-CoT outperforms the baselines consistently. The code is available at https://github.com/PeterGriffinJin/Graph-CoT.

Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction

Relation extraction (RE), a crucial task in NLP, aims to identify semantic relationships between entities mentioned in texts. Despite significant advancements in this field, existing models typically rely on extensive annotated data for training, which can be both costly and time-consuming to acquire. Moreover, these models often struggle to adapt to new or unseen relationships. In contrast, few-shot learning settings, which aim to reduce annotation requirements, may offer incomplete and biased supervision for understanding target relation semantics, leading to degraded and unstable performance. To provide the model with accurate and explicit descriptions of the relations types and meanwhile minimize the annotation requirements, we study the definition only zero-shot RE setting where only relation definitions expressed in natural language are used to train a RE model. Motivated by the strong synthetic data generation power of LLMs, we propose a framework REPaL which consists of three stages: (1) We utilize LLMs to generate initial seed instances based on relation definitions and an unlabeled corpora. (2) We fine-tune a bidirectional Small Language Model (SLM) using these initial seeds to learn the relations for the target domain. (3) We enhance pattern coverage and mitigate bias resulting from the limited number of initial seeds by incorporating feedback acquired from SLM's predictions on unlabeled corpora. To accomplish this, we leverage the multi-turn conversation ability of LLMs to generate new instances in follow-up dialogues. Experiments on two datasets show REPaL achieves better zero-shot performance with large margins over baseline methods.

SCStory: Self-supervised and Continual Online Story Discovery

We present a framework SCStory for online story discovery, that helps people digest rapidly published news article streams in real-time without human annotations. To organize news article streams into stories, existing approaches directly encode the articles and cluster them based on representation similarity. However, these methods yield noisy and inaccurate story discovery results because the generic article embeddings do not effectively reflect the story-indicative semantics in an article and cannot adapt to the rapidly evolving news article streams. SCStory employs self-supervised and continual learning with a novel idea of story-indicative adaptive modeling of news article streams. With a lightweight hierarchical embedding module that first learns sentence representations and then article representations, SCStory identifies story-relevant information of news articles and uses them to discover stories. The embedding module is continuously updated to adapt to evolving news streams with a contrastive learning objective, backed up by two unique techniques, confidence-aware memory replay and prioritized-augmentation, employed for label absence and data scarcity problems. Thorough experiments on real and the latest news data sets demonstrate that SCStory outperforms existing state-of-the-art algorithms for unsupervised online story discovery.

Rebuild City Buildings from Off-Nadir Aerial Images with Offset-Building Model

Accurate measurement of the offset from roof-to-footprint in very-high-resolution remote sensing imagery is crucial for urban information extraction tasks. With the help of deep learning, existing methods typically rely on two-stage CNN models to extract regions of interest on building feature maps. At the first stage, a Region Proposal Network (RPN) is applied to extract thousands of ROIs (Region of Interests) which will post-imported into a Region-based Convolutional Neural Networks (RCNN) to extract wanted information. However, because of inflexible RPN, these methods often lack effective user interaction, encounter difficulties in instance correspondence, and struggle to keep up with the advancements in general artificial intelligence. This paper introduces an interactive Transformer model combined with a prompt encoder to precisely extract building segmentation as well as the offset vectors from roofs to footprints. In our model, a powerful module, namely ROAM, was tailored for common problems in predicting roof-to-footprint offsets. We tested our model's feasibility on the publicly available BONAI dataset, achieving a significant reduction in Prompt-Instance-Level offset errors ranging from 14.6% to 16.3%. Additionally, we developed a Distance-NMS algorithm tailored for large-scale building offsets, significantly enhancing the accuracy of predicted building offset angles and lengths in a straightforward and efficient manner. To further validate the model's robustness, we created a new test set using 0.5m remote sensing imagery from Huizhou, China, for inference testing. Our code, training methods, and the updated dataset will be accessable at https://github.com/likaiucas.

Evaluating Large Language Models at Evaluating Instruction Following

As research in large language models (LLMs) continues to accelerate, LLM-based evaluation has emerged as a scalable and cost-effective alternative to human evaluations for comparing the ever increasing list of models. This paper investigates the efficacy of these "LLM evaluators", particularly in using them to assess instruction following, a metric that gauges how closely generated text adheres to the given instruction. We introduce a challenging meta-evaluation benchmark, LLMBar, designed to test the ability of an LLM evaluator in discerning instruction-following outputs. The authors manually curated 419 pairs of outputs, one adhering to instructions while the other diverging, yet may possess deceptive qualities that mislead an LLM evaluator, e.g., a more engaging tone. Contrary to existing meta-evaluation, we discover that different evaluators (i.e., combinations of LLMs and prompts) exhibit distinct performance on LLMBar and even the highest-scoring ones have substantial room for improvement. We also present a novel suite of prompting strategies that further close the gap between LLM and human evaluators. With LLMBar, we hope to offer more insight into LLM evaluators and foster future research in developing better instruction-following models.

Learning Multiplex Embeddings on Text-rich Networks with One Text Encoder

In real-world scenarios, texts in a network are often linked by multiple semantic relations (e.g., papers in an academic network are referenced by other publications, written by the same author, or published in the same venue), where text documents and their relations form a multiplex text-rich network. Mainstream text representation learning methods use pretrained language models (PLMs) to generate one embedding for each text unit, expecting that all types of relations between texts can be captured by these single-view embeddings. However, this presumption does not hold particularly in multiplex text-rich networks. Along another line of work, multiplex graph neural networks (GNNs) directly initialize node attributes as a feature vector for node representation learning, but they cannot fully capture the semantics of the nodes' associated texts. To bridge these gaps, we propose METERN, a new framework for learning Multiplex Embeddings on TExt-Rich Networks. In contrast to existing methods, METERN uses one text encoder to model the shared knowledge across relations and leverages a small number of parameters per relation to derive relation-specific representations. This allows the encoder to effectively capture the multiplex structures in the network while also preserving parameter efficiency. We conduct experiments on nine downstream tasks in five networks from both academic and e-commerce domains, where METERN outperforms baselines significantly and consistently. The code is available at https://github.com/PeterGriffinJin/METERN-submit.

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally rely on simple class-conditional prompts, which may limit the diversity of the generated data and inherit systematic biases of LLM. Thus, we investigate training data generation with diversely attributed prompts (e.g., specifying attributes like length and style), which have the potential to yield diverse and attributed generated data. Our investigation focuses on datasets with high cardinality and diverse domains, wherein we demonstrate that attributed prompts outperform simple class-conditional prompts in terms of the resulting model's performance. Additionally, we present a comprehensive empirical study on data generation encompassing vital aspects like bias, diversity, and efficiency, and highlight three key observations: firstly, synthetic datasets generated by simple prompts exhibit significant biases, such as regional bias; secondly, attribute diversity plays a pivotal role in enhancing model performance; lastly, attributed prompts achieve the performance of simple class-conditional prompts while utilizing only 5\% of the querying cost of ChatGPT associated with the latter. We release the generated dataset and used prompts to facilitate future research. The data and code will be available on \url{https://github.com/yueyu1030/AttrPrompt}.

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers

Instead of relying on human-annotated training samples to build a classifier, weakly supervised scientific paper classification aims to classify papers only using category descriptions (e.g., category names, category-indicative keywords). Existing studies on weakly supervised paper classification are less concerned with two challenges: (1) Papers should be classified into not only coarse-grained research topics but also fine-grained themes, and potentially into multiple themes, given a large and fine-grained label space; and (2) full text should be utilized to complement the paper title and abstract for classification. Moreover, instead of viewing the entire paper as a long linear sequence, one should exploit the structural information such as citation links across papers and the hierarchy of sections and paragraphs in each paper. To tackle these challenges, in this study, we propose FUTEX, a framework that uses the cross-paper network structure and the in-paper hierarchy structure to classify full-text scientific papers under weak supervision. A network-aware contrastive fine-tuning module and a hierarchy-aware aggregation module are designed to leverage the two types of structural signals, respectively. Experiments on two benchmark datasets demonstrate that FUTEX significantly outperforms competitive baselines and is on par with fully supervised classifiers that use 1,000 to 60,000 ground-truth training samples.

PromptClass: Weakly-Supervised Text Classification with Prompting Enhanced Noise-Robust Self-Training

Recently proposed weakly-supervised text classification settings train a classifier using the label name of each target class as the only supervision. Such weakly-supervised settings have been gaining increasing attention since they can largely reduce human annotation efforts compared to fully-supervised and semi-supervised settings. Most existing methods follow the strategy that first uses the label names as static features to generate pseudo labels, which are then used for classifier training. While reasonable, such a commonly adopted framework suffers from two limitations: (1) words can have different meanings in different contexts, so using label names for context-free matching can induce very noisy pseudo labels; and (2) the errors made in the pseudo label generation stage will directly propagate to the classifier training stage without a chance of being corrected. In this paper, we propose a new method, PromptClass, consisting of two modules: (1) a pseudo label acquisition module that uses zero-shot prompting of pre-trained language models (PLM) to get pseudo labels based on contextualized text understanding, and (2) a noise-robust self-training module that iteratively trains the classifier and updates pseudo labels by utilizing two PLM fine-tuning strategies that regularize each other. Extensive experiments show that PromptClass achieves overall better performance than existing strong baselines on four benchmark datasets and even achieves similar performance to fully-supervised classifiers on sentiment classification tasks.