New medical treatment development requires multiple phases of clinical trials. Despite the significant human and financial costs of bringing a drug to market, less than 20% of drugs in testing will make it from the first phase to final approval. Recent literature indicates that the design of the trial protocols significantly contributes to trial performance. We investigated Clinical Trial Outcome Prediction (CTOP) using trial design documents to predict phase transitions automatically. We propose CTP-LLM, the first Large Language Model (LLM) based model for CTOP. We also introduce the PhaseTransition (PT) Dataset; which labels trials based on their progression through the regulatory process and serves as a benchmark for CTOP evaluation. Our fine-tuned GPT-3.5-based model (CTP-LLM) predicts clinical trial phase transition by analyzing the trial's original protocol texts without requiring human-selected features. CTP-LLM achieves a 67% accuracy rate in predicting trial phase transitions across all phases and a 75% accuracy rate specifically in predicting the transition from Phase~III to final approval. Our experimental performance highlights the potential of LLM-powered applications in forecasting clinical trial outcomes and assessing trial design.

There is a wide variety of methods, tools and resources for processing text in the English language. However this is not the case for the Greek language even though it has a long documented history spanning at least 3,400 years of written records (including texts in syllabic script), and 28 centuries (Archaic period - new) of written text with alphabet [1, 2]. The over 2500 years literary tradition of Greek is also notable. To aid those that are interested in using, developing or advancing the techniques for Greek processing, in this paper we survey related works and resources organized in categories. We hope this collection and categorization of works to be useful for students and researchers interested in NLP tasks, Information Retrieval and Knowledge Management for the Greek language.

Many graph algorithms can be viewed as sets of rules that are iteratively applied, with the number of iterations dependent on the size and complexity of the input graph. Existing machine learning architectures often struggle to represent these algorithmic decisions as discrete state transitions. Therefore, we propose a novel framework: GraphFSA (Graph Finite State Automaton). GraphFSA is designed to learn a finite state automaton that runs on each node of a given graph. We test GraphFSA on cellular automata problems, showcasing its abilities in a straightforward algorithmic setting. For a comprehensive empirical evaluation of our framework, we create a diverse range of synthetic problems. As our main application, we then focus on learning more elaborate graph algorithms. Our findings suggest that GraphFSA exhibits strong generalization and extrapolation abilities, presenting an alternative approach to represent these algorithms.

The characters used in modern countries are mainly divided into ideographic characters and phonetic characters, both of which have their advantages and disadvantages. Chinese is difficult to learn and easy to master, while English is easy to learn but has a large vocabulary. There is still no language that combines the advantages of both languages and has less memory capacity, can form words, and is easy to learn. Therefore, inventing new characters that can be combined and the popularization of deep knowledge, and reduce disputes through communication. Firstly, observe the advantages and disadvantages of Chinese and English, such as their vocabulary, information content, and ease of learning in deep scientific knowledge, and create a new writing system. Then, use comparative analysis to observe the total score of the new language. Through this article, it can be concluded that the new text combines the advantages of both pictographic and alphabetical writing: new characters that can be combined into words reduces the vocabulary that needs to be learned; Special prefixes allow beginners to quickly guess the approximate category and meaning of unseen words; New characters can enable humans to quickly learn more advanced knowledge.

We find that the cross-entropy loss curves of neural language models empirically adhere to a scaling law with learning rate (LR) annealing over training steps ($s$): $$L(s) = L_0 + A\cdot S_1^{-\alpha} - C\cdot S_2$$ Where $S_1$ is forward area and $S_2$ is learning rate annealing area. This formulation takes into account two factors: (1) The forward scaling defined as typical scaling law, and (2) the additional loss drop brought by LR annealing. Therefore, this formulation can describe the full loss curve at each step, rather than the single loss point at the end of training. Applying the scaling law with LR annealing and fitting only one or two training curves, we can accurately predict the loss of language model training at any given step and across any learning rate scheduler (LRS). Furthermore, this equation accurately describes the dynamics during training process, and provides a theoretical verification and explanation for numerous experimental findings of previous studies, particularly those focusing on LR schedule and LR annealing. The resulting insights, also serve as a guide for researchers to select critical LRS in advance by prediction using our equation. Most significantly, since all the points in a full training curve follow the equation, we can achieve accurate loss prediction at any given step across any learning rate scheduler, while expending less than 1\% of the computational cost required by the chinchilla scaling law to fit language modeling loss. This approach extremely democratizes scaling law fitting and predicting in developing large language models.

The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large language models for text generation and diffusion models for visual generation, have sparked widespread research interest in applying these multimodal models in the fashion domain. However, tasks involving embeddings, such as image-to-text or text-to-image retrieval, have been largely overlooked from this perspective due to the diverse nature of the multimodal fashion domain. And current research on multi-task single models lack focus on image generation. In this work, we present UniFashion, a unified framework that simultaneously tackles the challenges of multimodal generation and retrieval tasks within the fashion domain, integrating image generation with retrieval tasks and text generation tasks. UniFashion unifies embedding and generative tasks by integrating a diffusion model and LLM, enabling controllable and high-fidelity generation. Our model significantly outperforms previous single-task state-of-the-art models across diverse fashion tasks, and can be readily adapted to manage complex vision-language tasks. This work demonstrates the potential learning synergy between multimodal generation and retrieval, offering a promising direction for future research in the fashion domain. The source code is available at https://github.com/xiangyu-mm/UniFashion.

The emergence of Large Language Models (LLMs) as chat assistants capable of generating human-like conversations has amplified the need for robust evaluation methods, particularly for open-ended tasks. Conventional metrics like BLEU and ROUGE, while useful, are increasingly inadequate for capturing the subtle semantics and contextual richness of such generative outputs. We propose a reference-guided verdict method that automates the evaluation process by leveraging multiple LLMs-as-judges. Through experiments on three open-ended question-answering tasks, we demonstrate that combining multiple LLMs-as-judges significantly improves the reliability and accuracy of evaluations, particularly in complex tasks where a single model might struggle. Our findings reveal a strong correlation with human evaluations, establishing our method as a viable and effective alternative to traditional metrics and human judgments, particularly in the context of LLM-based chat assistants where the complexity and diversity of responses challenge existing benchmarks.

Abstract--Domain-specific question answering remains challenging for language models, given the deep technical knowledge required to answer questions correctly. This difficulty is amplified for smaller language models that cannot encode as much information in their parameters as larger models. The "Specializing Large Language Models for Telecom Networks" challenge aimed to enhance the performance of two small language models, Phi-2 and Falcon-7B in telecommunication question answering. Our solutions achieved leading marks of 81.9% accuracy for Phi-2 and 57.3% for Falcon-7B. Advances in Large Language Models (LLMs) have significantly enhanced their performance across various Natural Language Processing (NLP) tasks.

Including code in the pre-training data mixture, even for models not specifically designed for code, has become a common practice in LLMs pre-training. While there has been anecdotal consensus among practitioners that code data plays a vital role in general LLMs' performance, there is only limited work analyzing the precise impact of code on non-code tasks. In this work, we systematically investigate the impact of code data on general performance. We ask "what is the impact of code data used in pre-training on a large variety of downstream tasks beyond code generation". We conduct extensive ablations and evaluate across a broad range of natural language reasoning tasks, world knowledge tasks, code benchmarks, and LLM-as-a-judge win-rates for models with sizes ranging from 470M to 2.8B parameters. Across settings, we find a consistent results that code is a critical building block for generalization far beyond coding tasks and improvements to code quality have an outsized impact across all tasks. In particular, compared to text-only pre-training, the addition of code results in up to relative increase of 8.2% in natural language (NL) reasoning, 4.2% in world knowledge, 6.6% improvement in generative win-rates, and a 12x boost in code performance respectively. Our work suggests investments in code quality and preserving code during pre-training have positive impacts.

Behavior cloning (BC) is a popular supervised imitation learning method in the societies of robotics, autonomous driving, etc., wherein complex skills can be learned by direct imitation from expert demonstrations. Despite its rapid development, it is still affected by limited field of view where accumulation of sensors and joint noise bring compounding errors. In this paper, we introduced geometrically and historically constrained behavior cloning (GHCBC) to dominantly consider high-level state information inspired by neuroscientists, wherein the geometrically constrained behavior cloning were used to geometrically constrain predicting poses, and the historically constrained behavior cloning were utilized to temporally constrain action sequences. The synergy between these two types of constrains enhanced the BC performance in terms of robustness and stability. Comprehensive experimental results showed that success rates were improved by 29.73% in simulation and 39.4% in real robot experiments in average, respectively, compared to state-of-the-art BC method, especially in long-term operational scenes, indicating great potential of using the GHCBC for robotic learning.