Large language models (LLMs) have shown impressive performance on language tasks but face challenges when deployed on resource-constrained devices due to their extensive parameters and reliance on dense multiplications, resulting in high memory demands and latency bottlenecks. Shift-and-add reparameterization offers a promising solution by replacing costly multiplications with hardware-friendly primitives in both the attention and multi-layer perceptron (MLP) layers of an LLM. However, current reparameterization techniques require training from scratch or full parameter fine-tuning to restore accuracy, which is resource-intensive for LLMs. To address this, we propose accelerating pretrained LLMs through post-training shift-and-add reparameterization, creating efficient multiplication-free models, dubbed ShiftAddLLM. Specifically, we quantize each weight matrix into binary matrices paired with group-wise scaling factors. The associated multiplications are reparameterized into (1) shifts between activations and scaling factors and (2) queries and adds according to the binary matrices. To reduce accuracy loss, we present a multi-objective optimization method to minimize both weight and output activation reparameterization errors. Additionally, based on varying sensitivity across layers to reparameterization, we develop an automated bit allocation strategy to further reduce memory usage and latency. Experiments on five LLM families and eight tasks consistently validate the effectiveness of ShiftAddLLM, achieving average perplexity improvements of 5.6 and 22.7 points at comparable or lower latency compared to the most competitive quantized LLMs at 3 and 2 bits, respectively, and more than 80% memory and energy reductions over the original LLMs. Codes and models are available at https://github.com/GATECH-EIC/ShiftAddLLM.

Recently, many methods have been developed to extend the context length of pre-trained large language models (LLMs), but they often require fine-tuning at the target length ( 4K) and struggle to effectively utilize information from the middle part of the context. To address these issues, we propose Continuity-Relativity indExing with gAussian Middle (CREAM), which interpolates positional encodings by manipulating position indices. Apart from being simple, CREAM is training-efficient: it only requires fine-tuning at the pre-trained context window (e.g., Llama 2-4K) and can extend LLMs to a much longer target context length (e.g., 256K). To ensure that the model focuses more on the information in the middle, we introduce a truncated Gaussian to encourage sampling from the middle part of the context during fine-tuning, thus alleviating the "Lost-in-the-Middle" problem faced by long-context LLMs. Experimental results show that CREAM successfully extends LLMs to the target length for both Base and Chat versions of Llama2-7B with "Never Miss A Beat". Our code will be publicly available soon.

Image description datasets play a crucial role in the advancement of various applications such as image understanding, text-to-image generation, and text-image retrieval. Currently, image description datasets primarily originate from two sources. One source is the scraping of image-text pairs from the web. Despite their abundance, these descriptions are often of low quality and noisy. Another is through human labeling. Datasets such as COCO are generally very short and lack details. Although detailed image descriptions can be annotated by humans, the high annotation cost limits the feasibility. These limitations underscore the need for more efficient and scalable methods to generate accurate and detailed image descriptions. In this paper, we propose an innovative framework termed Image Textualization (IT), which automatically produces high-quality image descriptions by leveraging existing multi-modal large language models (MLLMs) and multiple vision expert models in a collaborative manner, which maximally convert the visual information into text. To address the current lack of benchmarks for detailed descriptions, we propose several benchmarks for comprehensive evaluation, which verifies the quality of image descriptions created by our framework. Furthermore, we show that LLaVA-7B, benefiting from training on IT-curated descriptions, acquire improved capability to generate richer image descriptions, substantially increasing the length and detail of their output with less hallucination.

In games, and more generally in the field of software development, early detection of bugs is vital to maintain a high quality of the final product. Automated tests are a powerful tool that can catch a problem earlier in development by executing periodically. As an example, when new code is submitted to the code base, a new automated test verifies these changes. However, identifying the specific change responsible for a test failure becomes harder when dealing with batches of changes -- especially in the case of a large-scale project such as a AAA game, where thousands of people contribute to a single code base. This paper proposes a new approach to automatically identify which change in the code caused a test to fail. The method leverages Large Language Models (LLMs) to associate error messages with the corresponding code changes causing the failure. We investigate the effectiveness of our approach with quantitative and qualitative evaluations. Our approach reaches an accuracy of 71% in our newly created dataset, which comprises issues reported by developers at EA over a period of one year. We further evaluated our model through a user study to assess the utility and usability of the tool from a developer perspective, resulting in a significant reduction in time -- up to 60% -- spent investigating issues.

Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holistic evaluation to offer thorough insights into future improvements. In this work, we establish MultiTrust, the first comprehensive and unified benchmark on the trustworthiness of MLLMs across five primary aspects: truthfulness, safety, robustness, fairness, and privacy. Our benchmark employs a rigorous evaluation strategy that addresses both multimodal risks and cross-modal impacts, encompassing 32 diverse tasks with self-curated datasets. Extensive experiments with 21 modern MLLMs reveal some previously unexplored trustworthiness issues and risks, highlighting the complexities introduced by the multimodality and underscoring the necessity for advanced methodologies to enhance their reliability. For instance, typical proprietary models still struggle with the perception of visually confusing images and are vulnerable to multimodal jailbreaking and adversarial attacks; MLLMs are more inclined to disclose privacy in text and reveal ideological and cultural biases even when paired with irrelevant images in inference, indicating that the multimodality amplifies the internal risks from base LLMs. Additionally, we release a scalable toolbox for standardized trustworthiness research, aiming to facilitate future advancements in this important field. Code and resources are publicly available at: https://multi-trust.github.io/.

To fully leverage the capabilities of mobile manipulation robots, it is imperative that they are able to autonomously execute long-horizon tasks in large unexplored environments. While large language models (LLMs) have shown emergent reasoning skills on arbitrary tasks, existing work primarily concentrates on explored environments, typically focusing on either navigation or manipulation tasks in isolation. In this work, we propose MoMa-LLM, a novel approach that grounds language models within structured representations derived from open-vocabulary scene graphs, dynamically updated as the environment is explored. We tightly interleave these representations with an object-centric action space. Given object detections, the resulting approach is zero-shot, open-vocabulary, and readily extendable to a spectrum of mobile manipulation and household robotic tasks. We demonstrate the effectiveness of MoMa-LLM in a novel semantic interactive search task in large realistic indoor environments. In extensive experiments in both simulation and the real world, we show substantially improved search efficiency compared to conventional baselines and state-of-the-art approaches, as well as its applicability to more abstract tasks. We make the code publicly available at http://moma-llm.cs.uni-freiburg.de.

LLM-as-a-Judge offers a promising alternative to human judges across various tasks, yet inherent biases, particularly position bias - a systematic preference for answers based on their position in the prompt - compromise its effectiveness. Our study investigates this issue by developing a framework to systematically study and quantify position bias using metrics such as repetitional consistency, positional consistency, and positional fairness. We conduct experiments with 9 judge models across 22 tasks from the MTBench and DevBench benchmarks and nearly 40 answer-generating models, generating approximately 80,000 evaluation instances. This comprehensive assessment reveals significant variations in bias across judges and tasks. Although GPT-4 often excels in positional consistency and fairness, some more cost-effective models perform comparably or even better in specific tasks, highlighting essential trade-offs between consistency, fairness, and cost. Our results also demonstrate high consistency of judgment across repetitions, confirming that position bias is not due to random variations. This research significantly contributes to the field by introducing new concepts for understanding position bias and providing a multi-dimensional framework for evaluation. These insights guide the selection of optimal judge models, enhance benchmark design, and lay the foundation for future research into effective debiasing strategies, ultimately enhancing the reliability of LLM evaluators.

Personal health data, often derived from personal devices such as wearables, are distinguished by their multi-dimensional, continuous and longitudinal measurements that capture granular observations of physiology and behavior in-situ rather than in a clinical setting. Research studies have highlighted the significant health impacts of physical activity and sleep patterns, emphasizing the potential for wearable-derived data to reveal personalized health insights and promote positive behavior changes [1, 4, 30, 46, 47]. For example, individuals with a device-measured Physical Activity Energy Expenditure (PAEE) that is 5 kJ/kg/day higher had a 37% lower premature mortality risk [47]. Those with frequent sleep disturbances were associated with an increase in risk of hypertension, diabetes and cardiovascular diseases [9, 30]. A large meta-analysis suggests that activity trackers improve physical activity and promote weight loss, with users taking 1800 extra steps per day [16]. Despite these gross benefits, using wearable data to derive intelligent responses and insights to personal health queries is non-trivial. These data are usually collected without clinical supervision and users often do not have access to the expertise that could aid in data interpretation. For example, a common question of wearable device users is "How can I get better sleep?". Though a seemingly straightforward question, arriving at an ideal response would involve performing a series of complex, independent analytical steps across multiple irregularly sampled time series such as: checking the availability of recent data, deciding on metrics to optimize (e.g.

The reliance of popular programming languages such as Python and JavaScript on centralized package repositories and open-source software, combined with the emergence of code-generating Large Language Models (LLMs), has created a new type of threat to the software supply chain: package hallucinations. These hallucinations, which arise from fact-conflicting errors when generating code using LLMs, represent a novel form of package confusion attack that poses a critical threat to the integrity of the software supply chain. This paper conducts a rigorous and comprehensive evaluation of package hallucinations across different programming languages, settings, and parameters, exploring how different configurations of LLMs affect the likelihood of generating erroneous package recommendations and identifying the root causes of this phenomena. Using 16 different popular code generation models, across two programming languages and two unique prompt datasets, we collect 576,000 code samples which we analyze for package hallucinations. Our findings reveal that 19.7% of generated packages across all the tested LLMs are hallucinated, including a staggering 205,474 unique examples of hallucinated package names, further underscoring the severity and pervasiveness of this threat. We also implemented and evaluated mitigation strategies based on Retrieval Augmented Generation (RAG), self-detected feedback, and supervised fine-tuning. These techniques demonstrably reduced package hallucinations, with hallucination rates for one model dropping below 3%. While the mitigation efforts were effective in reducing hallucination rates, our study reveals that package hallucinations are a systemic and persistent phenomenon that pose a significant challenge for code generating LLMs.

Large language models (LLMs) have attracted great attention given their strong performance on a wide range of NLP tasks. In practice, users often expect generated texts to fall within a specific length range, making length controlled generation an important topic, especially for GPT-style models. Existing length control methods mostly focus on a simple control type of "equal to" a target length. Different from them, we propose a prompt-based method to achieve length controlled generation under different control types with high accuracy. In particular, we adopt reinforcement learning (RL) and sample filtering with the reward signal given by rule-based reward models, which enhances the length control ability of models by rewarding outputs that follow certain control instructions. In addition, we introduce a standard prompt extractor to parse arbitrary users' input into standard control instructions. Experiments show that our method significantly improves the accuracy of prompt-based length control on popular summarization datasets like CNNDM and NYT under multiple control types. Moreover, both the standard prompt extractor and RL-tuned model show strong generalization to unseen control prompt templates.