Positional encoding (PE) is essential for enabling Transformers to model sequential structure. However, the mechanisms by which different PE schemes couple token content and positional information-and how these mechanisms influence model dynamics-remain theoretically underexplored. In this work, we present a unified framework that analyzes PE through the spectral properties of Toeplitz and related matrices derived from attention logits. We show that multiplicative content-position coupling-exemplified by Rotary Positional Encoding (RoPE) via a Hadamard product with a Toeplitz matrix-induces spectral contraction, which theoretically improves optimization stability and efficiency. Guided by this theory, we construct synthetic tasks that contrast content-position dependent and content-position independent settings, and evaluate a range of PE methods. Our experiments reveal strong alignment with theory: RoPE consistently outperforms other methods on position-sensitive tasks and induces "single-head deposit" patterns in early layers, indicating localized positional processing. Further analyses show that modifying the method and timing of PE coupling, such as MLA in Deepseek-V3, can effectively mitigate this concentration. These results establish explicit content-relative mixing with relative-position Toeplitz signals as a key principle for effective PE design and provide new insight into how positional structure is integrated in Transformer architectures.

Airports from the top 20 in terms of annual passengers are highly dynamic environments with thousands of flights daily, and they aim to increase the degree of automation. To contribute to this, we implemented a Conversational AI system that enables staff in an airport to communicate with flight information systems. This system not only answers standard airport queries but also resolves airport terminology, jargon, abbreviations, and dynamic questions involving reasoning. In this paper, we built three different Retrieval-Augmented Generation (RAG) methods, including traditional RAG, SQL RAG, and Knowledge Graph-based RAG (Graph RAG). Experiments showed that traditional RAG achieved 84.84% accuracy using BM25 + GPT-4 but occasionally produced hallucinations, which is risky to airport safety. In contrast, SQL RAG and Graph RAG achieved 80.85% and 91.49% accuracy respectively, with significantly fewer hallucinations. Moreover, Graph RAG was especially effective for questions that involved reasoning. Based on our observations, we thus recommend SQL RAG and Graph RAG are better for airport environments, due to fewer hallucinations and the ability to handle dynamic questions.

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consistently underperform human experts in efficiency. Even the most efficient LLM-generated solutions (Qwen3-32B) achieve only around \textbf{62\%} of human efficiency on average, with significant language-specific variations. LLMs show better efficiency in Python, Ruby, and JavaScript than in Java, C++, and Golang. For instance, DeepSeek-R1's Python code is significantly more efficient than its Java code. These results highlight the critical need for research into LLM optimization techniques to improve code efficiency across diverse languages. The dataset and evaluation infrastructure are submitted and available at https://github.com/EffiBench/EffiBench-X.git and https://huggingface.co/datasets/EffiBench/effibench-x.

In recent years, the emergence of large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, has shown impressive capabilities in complex problems, e.g., mathematics and coding. Some pioneering studies attempt to bring the success of LRMs in neural machine translation (MT). They try to build LRMs with deep reasoning MT ability via reinforcement learning (RL). Despite some progress that has been made, these attempts generally focus on several high-resource languages, e.g., English and Chinese, leaving the performance on other languages unclear. Besides, the reward modeling methods in previous work do not fully unleash the potential of reinforcement learning in MT. In this work, we first design a new reward modeling method that compares the translation results of the policy MT model with a strong LRM (i.e., DeepSeek-R1-671B), and quantifies the comparisons to provide rewards. Experimental results demonstrate the superiority of the reward modeling method. Using Qwen2.5-7B-Instruct as the backbone, the trained model achieves the new state-of-the-art performance in literary translation, and outperforms strong LRMs including OpenAI-o1 and DeepSeeK-R1. Furthermore, we extend our method to the multilingual settings with 11 languages. With a carefully designed lightweight reward modeling in RL, we can simply transfer the strong MT ability from a single direction into multiple (i.e., 90) translation directions and achieve impressive multilingual MT performance.

Many-to-many summarization (M2MS) aims to process documents in any language and generate the corresponding summaries also in any language. Recently, large language models (LLMs) have shown strong multi-lingual abilities, giving them the potential to perform M2MS in real applications. This work presents a systematic empirical study on LLMs' M2MS ability. Specifically, we first reorganize M2MS data based on eight previous domain-specific datasets. The reorganized data contains 47.8K samples spanning five domains and six languages, which could be used to train and evaluate LLMs. Then, we benchmark 18 LLMs in a zero-shot manner and an instruction-tuning manner. Fine-tuned traditional models (e.g., mBART) are also conducted for comparisons. Our experiments reveal that, zero-shot LLMs achieve competitive results with fine-tuned traditional models. After instruct-tuning, open-source LLMs can significantly improve their M2MS ability, and outperform zero-shot LLMs (including GPT-4) in terms of automatic evaluations. In addition, we demonstrate that this task-specific improvement does not sacrifice the LLMs' general task-solving abilities. However, as revealed by our human evaluation, LLMs still face the factuality issue, and the instruction tuning might intensify the issue. Thus, how to control factual errors becomes the key when building LLM summarizers in real applications, and is worth noting in future research.

The continued rise of neural networks and large language models in the more recent past has altered the natural language processing landscape, enabling new approaches towards typical language tasks and achieving mainstream success. Despite the huge success of large language models, many disadvantages still remain and through this work we assess the state of the art in five application scenarios with a particular focus on the future perspectives and sensible application scenarios of traditional and older approaches and techniques. In this paper we survey recent publications in the application scenarios classification, information and relation extraction, text simplification as well as text summarization. After defining our terminology, i.e., which features are characteristic for traditional techniques in our interpretation for the five scenarios, we survey if such traditional approaches are still being used, and if so, in what way they are used. It turns out that all five application scenarios still exhibit traditional models in one way or another, as part of a processing pipeline, as a comparison/baseline to the core model of the respective paper, or as the main model(s) of the paper. For the complete statistics, see https://zenodo.org/records/13683801

Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning. We observe that for different queries, it could retrieve similar subgraphs as prompts, and thus we propose SubGCache, which aims to reduce inference latency by reusing computation across queries with similar structural prompts (i.e., subgraphs). Specifically, SubGCache clusters queries based on subgraph embeddings, constructs a representative subgraph for each cluster, and pre-computes the key-value (KV) cache of the representative subgraph. For each query with its retrieved subgraph within a cluster, it reuses the pre-computed KV cache of the representative subgraph of the cluster without computing the KV tensors again for saving computation. Experiments on two new datasets across multiple LLM backbones and graph-based RAG frameworks demonstrate that SubGCache consistently reduces inference latency with comparable and even improved generation quality, achieving up to 6.68$\times$ reduction in time-to-first-token (TTFT).

Robot task planning decomposes human instructions into executable action sequences that enable robots to complete a series of complex tasks. Although recent large language model (LLM)-based task planners achieve amazing performance, they assume that human instructions are clear and straightforward. However, real-world users are not experts, and their instructions to robots often contain significant vagueness. Linguists suggest that such vagueness frequently arises from referring expressions (REs), whose meanings depend heavily on dialogue context and environment. This vagueness is even more prevalent among the elderly and children, who robots should serve more. This paper studies how such vagueness in REs within human instructions affects LLM-based robot task planning and how to overcome this issue. To this end, we propose the first robot task planning benchmark with vague REs (REI-Bench), where we discover that the vagueness of REs can severely degrade robot planning performance, leading to success rate drops of up to 77.9%. We also observe that most failure cases stem from missing objects in planners. To mitigate the REs issue, we propose a simple yet effective approach: task-oriented context cognition, which generates clear instructions for robots, achieving state-of-the-art performance compared to aware prompt and chains of thought. This work contributes to the research community of human-robot interaction (HRI) by making robot task planning more practical, particularly for non-expert users, e.g., the elderly and children.

The use of Large Language Models (LLMs) in hardware design has taken off in recent years, principally through its incorporation in tools that increase chip designer productivity. There has been considerable discussion about the use of LLMs in RTL specifications of chip designs, for which the two most popular languages are Verilog and VHDL. LLMs and their use in Verilog design has received significant attention due to the higher popularity of the language, but little attention so far has been given to VHDL despite its continued popularity in the industry. There has also been little discussion about the unique needs of organizations that engage in high-performance processor design, and techniques to deploy AI solutions in these settings. In this paper, we describe our journey in developing a Large Language Model (LLM) specifically for the purpose of explaining VHDL code, a task that has particular importance in an organization with decades of experience and assets in high-performance processor design. We show how we developed test sets specific to our needs and used them for evaluating models as we performed extended pretraining (EPT) of a base LLM. Expert evaluation of the code explanations produced by the EPT model increased to 69% compared to a base model rating of 43%. We further show how we developed an LLM-as-a-judge to gauge models similar to expert evaluators. This led us to deriving and evaluating a host of new models, including an instruction-tuned version of the EPT model with an expected expert evaluator rating of 71%. Our experiments also indicate that with the potential use of newer base models, this rating can be pushed to 85% and beyond. We conclude with a discussion on further improving the quality of hardware design LLMs using exciting new developments in the Generative AI world.

We present a novel approach to symbolic regression using vision-capable large language models (LLMs) and the ideas behind Google DeepMind's Funsearch. The LLM is given a plot of a univariate function and tasked with proposing an ansatz for that function. The free parameters of the ansatz are fitted using standard numerical optimisers, and a collection of such ansätze make up the population of a genetic algorithm. Unlike other symbolic regression techniques, our method does not require the specification of a set of functions to be used in regression, but with appropriate prompt engineering, we can arbitrarily condition the generative step. By using Kolmogorov Arnold Networks (KANs), we demonstrate that ``univariate is all you need'' for symbolic regression, and extend this method to multivariate functions by learning the univariate function on each edge of a trained KAN. The combined expression is then simplified by further processing with a language model.