Integrated satellite, aerial, and terrestrial networks (ISATNs) represent a sophisticated convergence of diverse communication technologies to ensure seamless connectivity across different altitudes and platforms. This paper explores the transformative potential of integrating Large Language Models (LLMs) into ISATNs, leveraging advanced Artificial Intelligence (AI) and Machine Learning (ML) capabilities to enhance these networks. We outline the current architecture of ISATNs and highlight the significant role LLMs can play in optimizing data flow, signal processing, and network management to advance 5G/6G communication technologies through advanced predictive algorithms and real-time decision-making. A comprehensive analysis of ISATN components is conducted, assessing how LLMs can effectively address traditional data transmission and processing bottlenecks. The paper delves into the network management challenges within ISATNs, emphasizing the necessity for sophisticated resource allocation strategies, traffic routing, and security management to ensure seamless connectivity and optimal performance under varying conditions. Furthermore, we examine the technical challenges and limitations associated with integrating LLMs into ISATNs, such as data integration for LLM processing, scalability issues, latency in decision-making processes, and the design of robust, fault-tolerant systems. The study also identifies key future research directions for fully harnessing LLM capabilities in ISATNs, which is crucial for enhancing network reliability, optimizing performance, and achieving a truly interconnected and intelligent global network system.

In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs, limiting their ability to answer questions requiring an understanding of detailed or localized visual elements. Drawing inspiration from the Retrieval-Augmented Generation (RAG) concept, this paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models (e.g., instance segmentation/OCR models), into MLLMs. This is a promising yet underexplored direction for enhancing MLLMs' performance. Our approach diverges from concurrent works, which transform external knowledge into additional text prompts, necessitating the model to indirectly learn the correspondence between visual content and text coordinates. Instead, we propose embedding fine-grained knowledge information directly into a spatial embedding map as a visual prompt. This design can be effortlessly incorporated into various MLLMs, such as LLaVA and Mipha, considerably improving their visual understanding performance. Through rigorous experiments, we demonstrate that our method can enhance MLLM performance across nine benchmarks, amplifying their fine-grained context-aware capabilities.

Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself. Therefore, adapting linguistic structures within LLM training data to promote gender-inclusivity can make gender representations within the model more inclusive. The focus of our work are gender-exclusive affixes in English, such as in 'show-girl' or 'man-cave', which can perpetuate gender stereotypes and binary conceptions of gender. We use an LLM training dataset to compile a catalogue of 692 gender-exclusive terms along with gender-neutral variants and from this, develop a gender-inclusive fine-tuning dataset, the 'Tiny Heap'. Fine-tuning three different LLMs with this dataset, we observe an overall reduction in gender-stereotyping tendencies across the models. Our approach provides a practical method for enhancing gender inclusivity in LLM training data and contributes to incorporating queer-feminist linguistic activism in bias mitigation research in NLP.

Knowledge Base Question Answering (KBQA) has been a long-standing field to answer questions based on knowledge bases. Recently, the evolving dynamics of knowledge have attracted a growing interest in Temporal Knowledge Graph Question Answering (TKGQA), an emerging task to answer temporal questions. However, this field grapples with ambiguities in defining temporal questions and lacks a systematic categorization of existing methods for TKGQA. In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA. Specifically, we first establish a detailed taxonomy of temporal questions engaged in prior studies. Subsequently, we provide a comprehensive review of TKGQA techniques of two categories: semantic parsing-based and TKG embedding-based. Building on this review, the paper outlines potential research directions aimed at advancing the field of TKGQA. This work aims to serve as a comprehensive reference for TKGQA and to stimulate further research.

Automated Theorem Proving (ATP) faces significant challenges due to the vast action space and the computational demands of proof generation. Recent advances have utilized Large Language Models (LLMs) for action selection in ATP, but these methods often require substantial computational resources. This study introduces the Functional Equation Automated Solver (FEAS), an agent that builds on the COPRA in-context learning framework within the Lean environment. FEAS innovates by refining prompt generation and response parsing mechanisms, integrating domain-specific heuristics for functional equations, and introducing the FunEq dataset--a rigorously curated collection of functional equation problems categorized into three difficulty levels. The agent's performance is evaluated against established baselines using this dataset, demonstrating improvements in theorem proving accuracy, particularly with the integration of functional equation-specific heuristics. Our results highlight the effectiveness of FEAS in generating and formalizing high-level proof strategies into Lean proofs, emphasizing the potential of tailored approaches in domain-specific ATP challenges.

The rapid advancement of Large Language Models (LLMs) and Large Multimodal Models (LMMs) has heightened the demand for AI-based scientific assistants capable of understanding scientific articles and figures. Despite progress, there remains a significant gap in evaluating models' comprehension of professional, graduate-level, and even PhD-level scientific content. Current datasets and benchmarks primarily focus on relatively simple scientific tasks and figures, lacking comprehensive assessments across diverse advanced scientific disciplines. To bridge this gap, we collected a multimodal, multidisciplinary dataset from open-access scientific articles published in Nature Communications journals. This dataset spans 72 scientific disciplines, ensuring both diversity and quality. We created benchmarks with various tasks and settings to comprehensively evaluate LMMs' capabilities in understanding scientific figures and content. Our evaluation revealed that these tasks are highly challenging: many open-source models struggled significantly, and even GPT-4V and GPT-4o faced difficulties. We also explored using our dataset as training resources by constructing visual instruction-following data, enabling the 7B LLaVA model to achieve performance comparable to GPT-4V/o on our benchmark. Additionally, we investigated the use of our interleaved article texts and figure images for pre-training LMMs, resulting in improvements on the material generation task. The source dataset, including articles, figures, constructed benchmarks, and visual instruction-following data, is open-sourced.

Embodied AI robots have the potential to fundamentally improve the way human beings live and manufacture. Continued progress in the burgeoning field of using large language models to control robots depends critically on an efficient computing substrate. In particular, today's computing systems for embodied AI robots are designed purely based on the interest of algorithm developers, where robot actions are divided into a discrete frame-basis. Such an execution pipeline creates high latency and energy consumption. This paper proposes Corki, an algorithm-architecture co-design framework for real-time embodied AI robot control. Our idea is to decouple LLM inference, robotic control and data communication in the embodied AI robots compute pipeline. Instead of predicting action for one single frame, Corki predicts the trajectory for the near future to reduce the frequency of LLM inference. The algorithm is coupled with a hardware that accelerates transforming trajectory into actual torque signals used to control robots and an execution pipeline that parallels data communication with computation. Corki largely reduces LLM inference frequency by up to 8.0x, resulting in up to 3.6x speed up. The success rate improvement can be up to 17.3%. Code is provided for re-implementation. https://github.com/hyy0613/Corki

While Large Language Models (LLMs) excel in question-answering (QA) tasks, their multi-step reasoning abilities on multiple evidence integration on Multi-hop QA tasks remain underexplored. LLMs sometimes generate answers that rely on internal memory rather than reasoning given context, which brings concerns about the evaluation quality of real reasoning abilities. The counterfactual QA task can separate internal memory from reasoning abilities, but focusing solely on final-QA performance without evaluating the multi-step reasoning process is insufficient for reporting LLMs' real reasoning abilities. Current Multi-hop QA (MHQA) benchmarks are factual and annotated on open-source corpora such as Wikipedia, although useful for multi-step reasoning evaluation, showing limitations due to potential data contamination in LLMs pre-training stage. To address this issue, we introduce the Inherent Reasoning Evaluation (IRE) method, a novel evaluation way that jointly evaluates the LLMs' chain-of-reasoning performance based on the first knowledge-edited counterfactual multi-hop QA data which involves editing the original Wikipedia passages, reducing data contamination risks. The IRE comprehensively assesses reasoning chains through sub-QA and final-QA evaluations. Our comparisons reveal significant performance gaps for several LLMs between Wikipedia-based benchmarks and IRE, deeming data contamination issues in existing benchmarks. We believe that the IRE benchmark will enhance and facilitate trustworthy LLM evaluations.

Current hallucination detection and mitigation datasets are limited in domains and sizes, which struggle to scale due to prohibitive labor costs and insufficient reliability of existing hallucination annotators. To facilitate the scalable oversight of LLM hallucinations, this paper introduces an iterative self-training framework that simultaneously and progressively scales up the hallucination annotation dataset and improves the accuracy of the hallucination annotator. Based on the Expectation Maximization (EM) algorithm, in each iteration, the framework first applies a hallucination annotation pipeline to annotate a scaled dataset and then trains a more accurate hallucination annotator on the dataset. This new hallucination annotator is adopted in the hallucination annotation pipeline used for the next iteration. Extensive experimental results demonstrate that the finally obtained hallucination annotator with only 7B parameters surpasses the performance of GPT-4 and obtains new state-of-the-art hallucination detection results on HaluEval and HalluQA by zero-shot inference. Such an annotator can not only evaluate the hallucination levels of various LLMs on the large-scale dataset but also help to mitigate the hallucination of LLMs generations, with the Natural Language Inference (NLI) metric increasing from 25% to 37% on HaluEval.

The SLAM paper demonstrated that on-device Small Language Models (SLMs) are a viable and cost-effective alternative to API-based Large Language Models (LLMs), such as OpenAI's GPT-4, offering comparable performance and stability. However, SLAM also identified discrepancies between human preferences and traditional auto-evaluators. This follow-up paper explores methods to align LLM evaluator preferences with human evaluations by addressing biases, particularly toward higher token counts. We employed Bayesian statistics and a t-test to quantify this bias and developed a recalibration procedure to adjust the GPTScorer. Our findings significantly improve aligning the recalibrated LLM evaluator with human evaluations across multiple use cases. For instance, spearman's ranking correlation score in the Recommendation use case improved from -27.27 to 44.55. These results highlight the importance of accounting for biases in automated evaluations to ensure fair and accurate model assessments. The recalibration process enhances the reliability of automated evaluators, leading to better AI models that align with human values and expectations. This study provides a robust methodology for future research into bias correction and emphasizes the feasibility and benefits of developing human-aligned AI evaluation systems.