3D spatial understanding is essential in real-world applications such as robotics, autonomous vehicles, virtual reality, and medical imaging. Recently, Large Language Models (LLMs), having demonstrated remarkable success across various domains, have been leveraged to enhance 3D understanding tasks, showing potential to surpass traditional computer vision methods. In this survey, we present a comprehensive review of methods integrating LLMs with 3D spatial understanding. We propose a taxonomy that categorizes existing methods into three branches: image-based methods deriving 3D understanding from 2D visual data, point cloud-based methods working directly with 3D representations, and hybrid modality-based methods combining multiple data streams. We systematically review representative methods along these categories, covering data representations, architectural modifications, and training strategies that bridge textual and 3D modalities. Finally, we discuss current limitations, including dataset scarcity and computational challenges, while highlighting promising research directions in spatial perception, multi-modal fusion, and real-world applications.

Multimodal reasoning, which integrates language and visual cues into problem solving and decision making, is a fundamental aspect of human intelligence and a crucial step toward artificial general intelligence. However, the evaluation of multimodal reasoning capabilities in Multimodal Large Language Models (MLLMs) remains inadequate. Most existing reasoning benchmarks are constrained by limited data size, narrow domain coverage, and unstructured knowledge distribution. To close these gaps, we introduce MDK12-Bench, a multi-disciplinary benchmark assessing the reasoning capabilities of MLLMs via real-world K-12 examinations. Spanning six disciplines (math, physics, chemistry, biology, geography, and information science), our benchmark comprises 140K reasoning instances across diverse difficulty levels from primary school to 12th grade. It features 6,827 instance-level knowledge point annotations based on a well-organized knowledge structure, detailed answer explanations, difficulty labels and cross-year partitions, providing a robust platform for comprehensive evaluation. Additionally, we present a novel dynamic evaluation framework to mitigate data contamination issues by bootstrapping question forms, question types, and image styles during evaluation. Extensive experiment on MDK12-Bench reveals the significant limitation of current MLLMs in multimodal reasoning. The findings on our benchmark provide insights into the development of the next-generation models. Our data and codes are available at https://github.com/LanceZPF/MDK12.

Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs remain underexplored. In this study, we propose a layer-aware embedding selection method and investigate how to quantitatively evaluate different layers to identify the most important ones for downstream NLP tasks, showing that the critical layers vary depending on the dataset. We also explore how combining embeddings from multiple LLMs, without requiring model fine-tuning, can improve performance. Experiments on four English text classification datasets (SST-2, MR, R8, and R52) demonstrate that different layers in LLMs exhibit varying degrees of representational strength for classification, and that combining embeddings from different models can enhance performance if the models exhibit complementary characteristics. Additionally, we discuss resources overhead (memory and inference time) to provide a balanced perspective on the real world feasibility of embedding fusion. Future work will explore multilingual and domain specific datasets, as well as techniques for automating layer selection, to improve both performance and scalability.

In recent years, large language models (LLMs) achieve remarkable success across a variety of tasks. However, their potential in the domain of Automated Essay Scoring (AES) remains largely underexplored. Moreover, compared to English data, the methods for Chinese AES is not well developed. In this paper, we propose Rank-Then-Score (RTS), a fine-tuning framework based on large language models to enhance their essay scoring capabilities. Specifically, we fine-tune the ranking model (Ranker) with feature-enriched data, and then feed the output of the ranking model, in the form of a candidate score set, with the essay content into the scoring model (Scorer) to produce the final score. Experimental results on two benchmark datasets, HSK and ASAP, demonstrate that RTS consistently outperforms the direct prompting (Vanilla) method in terms of average QWK across all LLMs and datasets, and achieves the best performance on Chinese essay scoring using the HSK dataset.

Automatically assessing question quality is crucial for educators as it saves time, ensures consistency, and provides immediate feedback for refining teaching materials. We propose a novel methodology called STRIVE (Structured Thinking and Refinement with multiLLMs for Improving Verified Question Estimation) using a series of Large Language Models (LLMs) for automatic question evaluation. This approach aims to improve the accuracy and depth of question quality assessment, ultimately supporting diverse learners and enhancing educational practices. The method estimates question quality in an automated manner by generating multiple evaluations based on the strengths and weaknesses of the provided question and then choosing the best solution generated by the LLM. Then the process is improved by iterative review and response with another LLM until the evaluation metric values converge. This sophisticated method of evaluating question quality improves the estimation of question quality by automating the task of question quality evaluation. Correlation scores show that using this proposed method helps to improve correlation with human judgments compared to the baseline method. Error analysis shows that metrics like relevance and appropriateness improve significantly relative to human judgments by using STRIVE.

Conversational large language models (LLMs) have gained widespread attention due to their instruction-following capabilities. To ensure conversational LLMs follow instructions, role separators are employed to distinguish between different participants in a conversation. However, incorporating role separators introduces potential vulnerabilities. Misusing roles can lead to prompt injection attacks, which can easily misalign the model's behavior with the user's intentions, raising significant security concerns. Although various prompt injection attacks have been proposed, recent research has largely overlooked the impact of role separators on safety. This highlights the critical need to thoroughly understand the systemic weaknesses in dialogue systems caused by role separators. This paper identifies modeling weaknesses caused by role separators. Specifically, we observe a strong positional bias associated with role separators, which is inherent in the format of dialogue modeling and can be triggered by the insertion of role separators. We further develop the Separators Injection Attack (SIA), a new orthometric attack based on role separators. The experiment results show that SIA is efficient and extensive in manipulating model behavior with an average gain of 18.2% for manual methods and enhances the attack success rate to 100% with automatic methods.

This research paper presents a comprehensive analysis of the performance of prominent pre-trained large language models (LLMs), including GPT-4 Turbo, GPT-3.5 Turbo, text-davinci-003, text-babbage-001, text-curie-001, text-ada-001, llama-2-7b-chat, llama-2-13b-chat, and llama-2-70b-chat, in comparison to expert human evaluators in providing scores, identifying errors, and offering feedback and improvement suggestions to candidates during mock HR (Human Resources) interviews. We introduce a dataset called HURIT (Human Resource Interview Transcripts), which comprises 3,890 HR interview transcripts sourced from real-world HR interview scenarios. Our findings reveal that pre-trained LLMs, particularly GPT-4 Turbo and GPT-3.5 Turbo, exhibit commendable performance and are capable of producing evaluations comparable to those of expert human evaluators. Although these LLMs demonstrate proficiency in providing scores comparable to human experts in terms of human evaluation metrics, they frequently fail to identify errors and offer specific actionable advice for candidate performance improvement in HR interviews. Our research suggests that the current state-of-the-art pre-trained LLMs are not fully conducive for automatic deployment in an HR interview assessment. Instead, our findings advocate for a human-in-the-loop approach, to incorporate manual checks for inconsistencies and provisions for improving feedback quality as a more suitable strategy.

We propose a novel three-step prompt-tuning method for Bengali Grammatical Error Explanation (BGEE) using state-of-the-art large language models (LLMs) such as GPT-4, GPT-3.5 Turbo, and Llama-2-70b. Our approach involves identifying and categorizing grammatical errors in Bengali sentences, generating corrected versions of the sentences, and providing natural language explanations for each identified error. We evaluate the performance of our BGEE system using both automated evaluation metrics and human evaluation conducted by experienced Bengali language experts. Our proposed prompt-tuning approach shows that GPT-4, the best performing LLM, surpasses the baseline model in automated evaluation metrics, with a 5.26% improvement in F1 score and a 6.95% improvement in exact match. Furthermore, compared to the previous baseline, GPT-4 demonstrates a decrease of 25.51% in wrong error type and a decrease of 26.27% in wrong error explanation . However, the results still lag behind the human baseline.

DBOT can value any public traded company on the basis of Damodaran's analysis, and generates a report to support its position in an attempt to mimic its analytic parent. Until recently, such capabilities of analytic twins for financial valuation were not feasible. However, with advances in large language models (LLMs) and generative artificial intelligence (GenAI), it has become possible to conduct valuations that marry numbers and reasoning to generate credible valuations that can be used for long-term investing. The implications for automation and support of various parts of the valuation exercise are profound. In this paper, we provide a method for creating a digital analytic twin, DBOT, which is designed to mimic the investment analysis of individual companies by Damodaran. Since DBOT can value every company in an index such as the S&P500, it also provide an analysis in a macro sense, for example, by valuing the S&P500 market index relative to the valuation of its individual components. From the perspective of generative AI, DBOT presents a multitude of challenges. First and foremost, LLMs must be able to reason over financial texts, charts, tables, and spreadsheets. Furthermore, DBOT requires the AI system to follow Damodaran's

The increasing complexity of large language models (LLMs) necessitates efficient training strategies to mitigate the high computational costs associated with distributed training. A significant bottleneck in this process is gradient synchronization across multiple GPUs, particularly in the zero-redundancy parallelism mode. In this paper, we introduce Transformer-Aware Gradient Compression (TAGC), an optimized gradient compression algorithm designed specifically for transformer-based models. TAGC extends the lossless homomorphic compression method by adapting it for sharded models and incorporating transformer-specific optimizations, such as layer-selective compression and dynamic sparsification. Our experimental results demonstrate that TAGC accelerates training by up to 15% compared to the standard Fully Sharded Data Parallel (FSDP) approach, with minimal impact on model quality. We integrate TAGC into the PyTorch FSDP framework, the implementation is publicly available at https://github.com/ipolyakov/TAGC.