Large Language Models (LLMs) have immense potential to transform the telecommunications industry. They could help professionals understand complex standards, generate code, and accelerate development. However, traditional LLMs struggle with the precision and source verification essential for telecom work. To address this, specialized LLM-based solutions tailored to telecommunication standards are needed. Retrieval-augmented generation (RAG) offers a way to create precise, fact-based answers. This paper proposes TelecomRAG, a framework for a Telecommunication Standards Assistant that provides accurate, detailed, and verifiable responses. Our implementation, using a knowledge base built from 3GPP Release 16 and Release 18 specification documents, demonstrates how this assistant surpasses generic LLMs, offering superior accuracy, technical depth, and verifiability, and thus significant value to the telecommunications field.

Recent Large Language Models (LLMs) have demonstrated significant capabilities in generating code snippets directly from problem statements. This increasingly automated process mirrors traditional human-led software development, where code is often written in response to a requirement. Historically, Test-Driven Development (TDD) has proven its merit, requiring developers to write tests before the functional code, ensuring alignment with the initial problem statements. Applying TDD principles to LLM-based code generation offers one distinct benefit: it enables developers to verify the correctness of generated code against predefined tests. This paper investigates if and how TDD can be incorporated into AI-assisted code-generation processes. We experimentally evaluate our hypothesis that providing LLMs like GPT-4 and Llama 3 with tests in addition to the problem statements enhances code generation outcomes. We experimented with established function-level code generation benchmarks such as MBPP and HumanEval. Our results consistently demonstrate that including test cases leads to higher success in solving programming challenges. We assert that TDD is a promising paradigm for helping ensure that the code generated by LLMs effectively captures the requirements.

LLM text decoding is key component for perceived LLM quality. We demonstrate two experiments showing that decoding methods could be improved by manipulation of token probabilities. First, we test few LLM on SummEval summary scoring dataset, to measure reading comprehension. We compare scores from greedy decoding to expected values over the next token distribution. We scale logits by large temperature to increase the entropy of scores. This allows strong improvement of performance on SummEval (in terms of correlations to human judgement). We see improvement from 6-8% to 13-28% for 7B Mistral and from 20%-46% to 37%-56% for Mixtral, beating GPT 4 0314 result on two metrics. Part of the gain seems related to positional bias. Secondly, we use probability-based tree sampling algorithm, to examine all most probable generations for given prompt.

As the capabilities of LLMs expand, it becomes increasingly important to evaluate them beyond basic knowledge assessment, focusing on higher-level language understanding. This study introduces MultiPragEval, a robust test suite designed for the multilingual pragmatic evaluation of LLMs across English, German, Korean, and Chinese. Comprising 1200 question units categorized according to Grice's Cooperative Principle and its four conversational maxims, MultiPragEval enables an in-depth assessment of LLMs' contextual awareness and their ability to infer implied meanings. Our findings demonstrate that Claude3-Opus significantly outperforms other models in all tested languages, establishing a state-of-the-art in the field. Among open-source models, Solar-10.7B and Qwen1.5-14B emerge as strong competitors. This study not only leads the way in the multilingual evaluation of LLMs in pragmatic inference but also provides valuable insights into the nuanced capabilities necessary for advanced language comprehension in AI systems.

The advent of Large Language Models (LLMs) has revolutionized text generation, producing outputs that closely mimic human writing. This blurring of lines between machine- and human-written text presents new challenges in distinguishing one from the other a task further complicated by the frequent updates and closed nature of leading proprietary LLMs. Traditional logits-based detection methods leverage surrogate models for identifying LLM-generated content when the exact logits are unavailable from black-box LLMs. However, these methods grapple with the misalignment between the distributions of the surrogate and the often undisclosed target models, leading to performance degradation, particularly with the introduction of new, closed-source models. Furthermore, while current methodologies are generally effective when the source model is identified, they falter in scenarios where the model version remains unknown, or the test set comprises outputs from various source models. To address these limitations, we present Distribution-Aligned LLMs Detection (DALD), an innovative framework that redefines the state-of-the-art performance in black-box text detection even without logits from source LLMs. DALD is designed to align the surrogate model's distribution with that of unknown target LLMs, ensuring enhanced detection capability and resilience against rapid model iterations with minimal training investment. By leveraging corpus samples from publicly accessible outputs of advanced models such as ChatGPT, GPT-4 and Claude-3, DALD fine-tunes surrogate models to synchronize with unknown source model distributions effectively.

Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to enhance their reasoning capabilities on complex tasks, thus taking on the role of intelligent agents interacting with the real world. The recently introduced ToolLLaMA model by Qin et al. [2024] utilizes the depth-first search-based decision tree (DFSDT) method for reasoning with $16000+$ real-world APIs, which effectively improves the planning and inferencing performance of tool-augmented LLMs compared to traditional chain reasoning approaches. However, their approach only employs successful paths from decision trees (also called inference trees) for supervised fine-tuning (SFT) during training, which does not fully exploit the advantages of the tree of thought. In this study, we propose an inference trajectory optimization framework based on the preference data extracted from decision trees to address this limitation. We first introduce a novel method for constructing preference data from the tree of thought, capitalizing on the failed explorations previously overlooked in the trees. Specifically, we generate an effective step-wise preference dataset, named ToolPreference, for tool use based on the ToolBench dataset. In the subsequent training phase, we first fine-tune the LLM with tool-usage expert trajectories and then use these step-wise preference pairs for direct preference optimization (DPO) to update the policy of the LLM, resulting in our ToolPrefer-LLaMA (TP-LLaMA) model. Our experiments demonstrate that by obtaining insights from errors in inference trees, TP-LLaMA significantly outperforms the baselines across almost all test scenarios by a large margin and exhibits better generalization capabilities with unseen APIs. At the same time, TP-LLaMA has also demonstrated superior reasoning efficiency compared to the baselines, making it more suitable for complex tool-usage reasoning tasks.

Extending large language models (LLMs) to process longer inputs is crucial for a wide range of applications. However, the substantial computational cost of transformers and limited generalization of positional encoding restrict the size of their context window. We introduce Context Expansion with Parallel Encoding (CEPE), a framework that can be applied to any existing decoder-only LLMs to extend their context window. CEPE employs a small encoder to process long inputs chunk by chunk, enabling the frozen decoder to utilize additional contexts via cross-attention. CEPE is efficient, generalizable, and versatile: trained with 8K-token documents, it extends the context window of LLAMA-2 to 128K tokens, offering 10x the throughput with only 1/6 of the memory. CEPE yields strong performance on language modeling and in-context learning. CEPE also excels in retrieval-augmented applications, while existing long-context models degenerate with retrieved contexts. We further introduce a CEPE variant that can extend the context window of instruction-tuned models using only unlabeled data, and showcase its effectiveness on LLAMA-2-CHAT, leading to a strong instruction-following model that can leverage very long contexts on downstream tasks.

Few-shot gradient methods have been extensively utilized in existing model pruning methods, where the model weights are regarded as static values and the effects of potential weight perturbations are not considered. However, the widely used large language models (LLMs) have several billion model parameters, which could increase the fragility of few-shot gradient pruning. In this work, we experimentally show that one-shot gradient pruning algorithms could lead to unstable results under perturbations to model weights. And the minor error of switching between data formats bfloat16 and float16 could result in drastically different outcomes. To address such instabilities, we leverage optimization analysis and propose an LLM structural pruning method, called MoreauPruner, with provable robustness against weight perturbations. In MoreauPruner, the model weight importance is estimated based on the neural network's Moreau envelope, which can be flexibly combined with $\ell_1$-norm regularization techniques to induce the sparsity required in the pruning task. We extensively evaluate the MoreauPruner algorithm on several well-known LLMs, including LLaMA-7B, LLaMA-13B, LLaMA3-8B, and Vicuna-7B. Our numerical results suggest the robustness of MoreauPruner against weight perturbations, and indicate the MoreauPruner's successful accuracy-based scores in comparison to several existing pruning methods. We have released the code in \url{https://github.com/ShiningSord/MoreauPruner}.

Foundation vision-language models have enabled remarkable zero-shot transferability of the pre-trained representations to a wide range of downstream tasks. However, to solve a new task, zero-shot transfer still necessitates human guidance to define visual categories that appear in the data. Here, we show that fully unsupervised transfer emerges when searching for the labeling of a dataset that induces maximal margin classifiers in representation spaces of different foundation models. We present TURTLE, a fully unsupervised method that effectively employs this guiding principle to uncover the underlying labeling of a downstream dataset without any supervision and task-specific representation learning. We evaluate TURTLE on a diverse benchmark suite of 26 datasets and show that it achieves new state-of-the-art unsupervised performance. Furthermore, TURTLE, although being fully unsupervised, outperforms zero-shot transfer baselines on a wide range of datasets. In particular, TURTLE matches the average performance of CLIP zero-shot on 26 datasets by employing the same representation space, spanning a wide range of architectures and model sizes. By guiding the search for the underlying labeling using the representation spaces of two foundation models, TURTLE surpasses zero-shot transfer and unsupervised prompt tuning baselines, demonstrating the surprising power and effectiveness of unsupervised transfer.

Recent sequence modeling approaches using Selective State Space Sequence Models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being adopted in a wide range of applications such as language modeling, demonstrating promising performance. To foster their reliable use in real-world scenarios, it is crucial to augment their transparency. Our work bridges this critical gap by bringing explainability, particularly Layer-wise Relevance Propagation (LRP), to the Mamba architecture. Guided by the axiom of relevance conservation, we identify specific components in the Mamba architecture, which cause unfaithful explanations. To remedy this issue, we propose MambaLRP, a novel algorithm within the LRP framework, which ensures a more stable and reliable relevance propagation through these components. Our proposed method is theoretically sound and excels in achieving state-of-the-art explanation performance across a diverse range of models and datasets. Moreover, MambaLRP facilitates a deeper inspection of Mamba architectures, uncovering various biases and evaluating their significance. It also enables the analysis of previous speculations regarding the long-range capabilities of Mamba models.