Jerry Junyang Cheung, Yuchen Zhuang, Yinghao Li et al. · gatech
Scientific information extraction (SciIE), which aims to automatically extract information from scientific literature, is becoming more important than ever. However, there are no existing SciIE datasets for polymer materials, which is an important class of materials used ubiquitously in our daily lives. To bridge this gap, we introduce POLYIE, a new SciIE dataset for polymer materials. POLYIE is curated from 146 full-length polymer scholarly articles, which are annotated with different named entities (i.e., materials, properties, values, conditions) as well as their N-ary relations by domain experts. POLYIE presents several unique challenges due to diverse lexical formats of entities, ambiguity between entities, and variable-length relations. We evaluate state-of-the-art named entity extraction and relation extraction models on POLYIE, analyze their strengths and weaknesses, and highlight some difficult cases for these models. To the best of our knowledge, POLYIE is the first SciIE benchmark for polymer materials, and we hope it will lead to more research efforts from the community on this challenging task. Our code and data are available on: https://github.com/jerry3027/PolyIE.
Yuchen Zhuang, Yinghao Li, Jerry Junyang Cheung et al. · gatech
We study the problem of extracting N-ary relation tuples from scientific articles. This task is challenging because the target knowledge tuples can reside in multiple parts and modalities of the document. Our proposed method ReSel decomposes this task into a two-stage procedure that first retrieves the most relevant paragraph/table and then selects the target entity from the retrieved component. For the high-level retrieval stage, ReSel designs a simple and effective feature set, which captures multi-level lexical and semantic similarities between the query and components. For the low-level selection stage, ReSel designs a cross-modal entity correlation graph along with a multi-view architecture, which models both semantic and document-structural relations between entities. Our experiments on three scientific information extraction datasets show that ReSel outperforms state-of-the-art baselines significantly.
Yinghao Li, Lingkai Kong, Yuanqi Du et al. · gatech
Large molecular representation models pre-trained on massive unlabeled data have shown great success in predicting molecular properties. However, these models may tend to overfit the fine-tuning data, resulting in over-confident predictions on test data that fall outside of the training distribution. To address this issue, uncertainty quantification (UQ) methods can be used to improve the models' calibration of predictions. Although many UQ approaches exist, not all of them lead to improved performance. While some studies have included UQ to improve molecular pre-trained models, the process of selecting suitable backbone and UQ methods for reliable molecular uncertainty estimation remains underexplored. To address this gap, we present MUBen, which evaluates different UQ methods for state-of-the-art backbone molecular representation models to investigate their capabilities. By fine-tuning various backbones using different molecular descriptors as inputs with UQ methods from different categories, we assess the influence of architectural decisions and training strategies. Our study offers insights for selecting UQ for backbone models, which can facilitate research on uncertainty-critical applications in fields such as materials science and drug discovery.
Large Language Models (LLMs) have shown remarkable proficiency in language understanding and have been successfully applied to a variety of real-world tasks through task-specific fine-tuning or prompt engineering. Despite these advancements, it remains an open question whether LLMs are fundamentally capable of reasoning and planning, or if they primarily rely on recalling and synthesizing information from their training data. In our research, we introduce a novel task -- Minesweeper -- specifically designed in a format unfamiliar to LLMs and absent from their training datasets. This task challenges LLMs to identify the locations of mines based on numerical clues provided by adjacent opened cells. Successfully completing this task requires an understanding of each cell's state, discerning spatial relationships between the clues and mines, and strategizing actions based on logical deductions drawn from the arrangement of the cells. Our experiments, including trials with the advanced GPT-4 model, indicate that while LLMs possess the foundational abilities required for this task, they struggle to integrate these into a coherent, multi-step logical reasoning process needed to solve Minesweeper. These findings highlight the need for further research to understand the nature of reasoning capabilities in LLMs under similar circumstances, and to explore pathways towards more sophisticated AI reasoning and planning models.
Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence. While general artificial intelligence is leveraged by developing increasingly large-scale models, there could be another branch to develop lightweight custom models that better serve certain domains, taking into account the high cost of training and deploying LLMs and the scarcity of resources. In this paper, we present MindLLM, a novel series of bilingual lightweight large language models, trained from scratch, alleviating such burdens by offering models with 1.3 billion and 3 billion parameters. A thorough account of experiences accrued during large model development is given, covering every step of the process, including data construction, model architecture, evaluation, and applications. Such insights are hopefully valuable for fellow academics and developers. MindLLM consistently matches or surpasses the performance of other open-source larger models on some public benchmarks. We also introduce an innovative instruction tuning framework tailored for smaller models to enhance their capabilities efficiently. Moreover, we explore the application of MindLLM in specific vertical domains such as law and finance, underscoring the agility and adaptability of our lightweight models.
We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN decouples representational width from backbone width, expanding the embedding space while keeping backbone compute nearly constant. In our large-scale experiment, an 8-times expansion accelerates optimization by over 2 times for next-token and 3 times for next-2-token prediction. The advantage amplifies over training as both the loss gap grows and the convergence-speedup ratio increases, showing that VWN is not only token-efficient but also increasingly effective with scale. Moreover, we identify an approximately log-linear scaling relation between virtual width and loss reduction, offering an initial empirical basis and motivation for exploring virtual-width scaling as a new dimension of large-model efficiency.
Weak labeling is a popular weak supervision strategy for Named Entity Recognition (NER) tasks, with the goal of reducing the necessity for hand-crafted annotations. Although there are numerous remarkable annotation tools for NER labeling, the subject of integrating weak labeling sources is still unexplored. We introduce a web-based tool for text annotation called SciAnnotate, which stands for scientific annotation tool. Compared to frequently used text annotation tools, our annotation tool allows for the development of weak labels in addition to providing a manual annotation experience. Our tool provides users with multiple user-friendly interfaces for creating weak labels. SciAnnotate additionally allows users to incorporate their own language models and visualize the output of their model for evaluation. In this study, we take multi-source weak label denoising as an example, we utilized a Bertifying Conditional Hidden Markov Model to denoise the weak label generated by our tool. We also evaluate our annotation tool against the dataset provided by Mysore which contains 230 annotated materials synthesis procedures. The results shows that a 53.7% reduction in annotation time obtained AND a 1.6\% increase in recall using weak label denoising. Online demo is available at https://sciannotate.azurewebsites.net/(demo account can be found in README), but we don't host a model server with it, please check the README in supplementary material for model server usage.
Rushi Qiang, Yuchen Zhuang, Yinghao Li et al. · gatech
We introduce MLE-Dojo, a Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows. Unlike existing benchmarks that primarily rely on static datasets or single-attempt evaluations, MLE-Dojo provides an interactive environment enabling agents to iteratively experiment, debug, and refine solutions through structured feedback loops. Built upon 200+ real-world Kaggle challenges, MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios such as data processing, architecture search, hyperparameter tuning, and code debugging. Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating iterative experimentation, realistic data sampling, and real-time outcome verification. Extensive evaluations of eight frontier LLMs reveal that while current models achieve meaningful iterative improvements, they still exhibit significant limitations in autonomously generating long-horizon solutions and efficiently resolving complex errors. Furthermore, MLE-Dojo's flexible and extensible architecture seamlessly integrates diverse data sources, tools, and evaluation protocols, uniquely enabling model-based agent tuning and promoting interoperability, scalability, and reproducibility. We open-source our framework and benchmarks to foster community-driven innovation towards next-generation MLE agents.
Language style is necessary for AI systems to understand and generate diverse human language accurately. However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of LLMs. For such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts. Comprehensive experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information.
Jerry Junyang Cheung, Shiyao Shen, Yuchen Zhuang et al. · gatech
Despite recent advances in large language models (LLMs) for materials science, there is a lack of benchmarks for evaluating their domain-specific knowledge and complex reasoning abilities. To bridge this gap, we introduce MSQA, a comprehensive evaluation benchmark of 1,757 graduate-level materials science questions in two formats: detailed explanatory responses and binary True/False assessments. MSQA distinctively challenges LLMs by requiring both precise factual knowledge and multi-step reasoning across seven materials science sub-fields, such as structure-property relationships, synthesis processes, and computational modeling. Through experiments with 10 state-of-the-art LLMs, we identify significant gaps in current LLM performance. While API-based proprietary LLMs achieve up to 84.5% accuracy, open-source (OSS) LLMs peak around 60.5%, and domain-specific LLMs often underperform significantly due to overfitting and distributional shifts. MSQA represents the first benchmark to jointly evaluate the factual and reasoning capabilities of LLMs crucial for LLMs in advanced materials science.
Recent Weak Supervision (WS) approaches have had widespread success in easing the bottleneck of labeling training data for machine learning by synthesizing labels from multiple potentially noisy supervision sources. However, proper measurement and analysis of these approaches remain a challenge. First, datasets used in existing works are often private and/or custom, limiting standardization. Second, WS datasets with the same name and base data often vary in terms of the labels and weak supervision sources used, a significant "hidden" source of evaluation variance. Finally, WS studies often diverge in terms of the evaluation protocol and ablations used. To address these problems, we introduce a benchmark platform, WRENCH, for thorough and standardized evaluation of WS approaches. It consists of 22 varied real-world datasets for classification and sequence tagging; a range of real, synthetic, and procedurally-generated weak supervision sources; and a modular, extensible framework for WS evaluation, including implementations for popular WS methods. We use WRENCH to conduct extensive comparisons over more than 120 method variants to demonstrate its efficacy as a benchmark platform. The code is available at https://github.com/JieyuZ2/wrench.
We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications. The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at https://github.com/weakrules/Denoise-multi-weak-sources.
Taxonomies are important knowledge ontologies that underpin numerous applications on a daily basis, but many taxonomies used in practice suffer from the low coverage issue. We study the taxonomy expansion problem, which aims to expand existing taxonomies with new concept terms. We propose a self-supervised taxonomy expansion model named STEAM, which leverages natural supervision in the existing taxonomy for expansion. To generate natural self-supervision signals, STEAM samples mini-paths from the existing taxonomy, and formulates a node attachment prediction task between anchor mini-paths and query terms. To solve the node attachment task, it learns feature representations for query-anchor pairs from multiple views and performs multi-view co-training for prediction. Extensive experiments show that STEAM outperforms state-of-the-art methods for taxonomy expansion by 11.6\% in accuracy and 7.0\% in mean reciprocal rank on three public benchmarks. The implementation of STEAM can be found at \url{https://github.com/yueyu1030/STEAM}.
Large language models (LLMs) have demonstrated impressive abilities in generating unstructured natural language according to instructions. However, their performance can be inconsistent when tasked with producing text that adheres to specific structured formats, which is crucial in applications like named entity recognition (NER) or relation extraction (RE). To address this issue, this paper introduces an efficient method, G&O, to enhance their structured text generation capabilities. It breaks the generation into a two-step pipeline: initially, LLMs generate answers in natural language as intermediate responses. Subsequently, LLMs are asked to organize the output into the desired structure, using the intermediate responses as context. G&O effectively separates the generation of content from the structuring process, reducing the pressure of completing two orthogonal tasks simultaneously. Tested on zero-shot NER and RE, the results indicate a significant improvement in LLM performance with minimal additional efforts. This straightforward and adaptable prompting technique can also be combined with other strategies, like self-consistency, to further elevate LLM capabilities in various structured text generation tasks.
Yuzhao Heng, Chunyuan Deng, Yitong Li et al. · gatech
Although Large Language Models (LLMs) exhibit remarkable adaptability across domains, these models often fall short in structured knowledge extraction tasks such as named entity recognition (NER). This paper explores an innovative, cost-efficient strategy to harness LLMs with modest NER capabilities for producing superior NER datasets. Our approach diverges from the basic class-conditional prompts by instructing LLMs to self-reflect on the specific domain, thereby generating domain-relevant attributes (such as category and emotions for movie reviews), which are utilized for creating attribute-rich training data. Furthermore, we preemptively generate entity terms and then develop NER context data around these entities, effectively bypassing the LLMs' challenges with complex structures. Our experiments across both general and niche domains reveal significant performance enhancements over conventional data generation methods while being more cost-effective than existing alternatives.
Yinghao Li, Vianne Gao, Chao Zhang et al. · gatech
The training and fine-tuning of large language models (LLMs) often involve diverse textual data from multiple sources, which poses challenges due to conflicting gradient directions, hindering optimization and specialization. These challenges can undermine model generalization across tasks, resulting in reduced downstream performance. Recent research suggests that fine-tuning LLMs on carefully selected, task-specific subsets of data can match or even surpass the performance of using the entire dataset. Building on these insights, we propose the Ensembles of Low-Rank Expert Adapters (ELREA) framework to improve the model's capability to handle diverse tasks. ELREA clusters the training instructions based on their gradient directions, representing different areas of expertise and thereby reducing conflicts during optimization. Expert adapters are then trained on these clusters, utilizing the low-rank adaptation (LoRA) technique to ensure training efficiency and model scalability. During inference, ELREA combines predictions from the most relevant expert adapters based on the input data's gradient similarity to the training clusters, ensuring optimal adapter selection for each task. Experiments show that our method outperforms baseline LoRA adapters trained on the full dataset and other ensemble approaches with similar training and inference complexity across a range of domain-specific tasks.
Domain adaptation aims to enable Large Language Models (LLMs) to generalize domain datasets unseen effectively during the training phase. However, factors such as the size of the model parameters and the scale of training data are general influencers and do not reflect the nuances of domain adaptation performance. This paper investigates the fine-grained factors affecting domain adaptation performance, analyzing the specific impact of `words' in training data on summarization tasks. We propose quantifying dataset learning difficulty as the learning difficulty of generative summarization, which is determined by two indicators: word-based compression rate and abstraction level. Our experiments conclude that, when considering dataset learning difficulty, the cross-domain overlap and the performance gain in summarization tasks exhibit an approximate linear relationship, which is not directly related to the number of words. Based on this finding, predicting a model's performance on unknown domain datasets is possible without undergoing training.
We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem but also falls short in modeling the tree structure of the syntactic guidance. We propose to leverage the parallelism of Transformer to better incorporate parse trees. Our method first expands a partial template constituency parse tree to a full-fledged parse tree tailored for the input source text, and then uses the expanded tree to guide text generation. The effectiveness of our model in this process hinges upon two new attention mechanisms: 1) a path attention mechanism that forces one node to attend to only other nodes located in its path in the syntax tree to better incorporate syntax guidance; 2) a multi-encoder attention mechanism that allows the decoder to dynamically attend to information from multiple encoders. Our experiments in the controlled paraphrasing task show that our method outperforms SOTA models both semantically and syntactically, improving the best baseline's BLEU score from 11.83 to 26.27.