This position paper investigates the potential of integrating insights from language impairment research and its clinical treatment to develop human-inspired learning strategies and evaluation frameworks for language models (LMs). We inspect the theoretical underpinnings underlying some influential linguistically motivated training approaches derived from neurolinguistics and, particularly, aphasiology, aimed at enhancing the recovery and generalization of linguistic skills in aphasia treatment, with a primary focus on those targeting the syntactic domain. We highlight how these insights can inform the design of rigorous assessments for LMs, specifically in their handling of complex syntactic phenomena, as well as their implications for developing human-like learning strategies, aligning with efforts to create more sustainable and cognitively plausible natural language processing (NLP) models.
This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the language foundation model during the action instruction tuning phase, making them unsuitable for this purpose. We introduce a novel latency-free quadruped MLLM model, dubbed QUART-Online, designed to enhance inference efficiency without degrading the performance of the language foundation model. By incorporating Action Chunk Discretization (ACD), we compress the original action representation space, mapping continuous action values onto a smaller set of discrete representative vectors while preserving critical information. Subsequently, we fine-tune the MLLM to integrate vision, language, and compressed actions into a unified semantic space. Experimental results demonstrate that QUART-Online operates in tandem with the existing MLLM system, achieving real-time inference in sync with the underlying controller frequency, significantly boosting the success rate across various tasks by 65%. Our project page is https://quart-online.github.io.
Japan Agency for Marine-Earth Science and Technology (JAMSTEC) has made available the JAMSTEC Earth Deep-sea Image (J-EDI), a deep-sea video and image archive (https://www.godac.jamstec.go.jp/jedi/e/index.html). This archive serves as a valuable resource for researchers and scholars interested in deep-sea imagery. The dataset comprises images and videos of deep-sea phenomena, predominantly of marine organisms, but also of the seafloor and physical processes. In this study, we propose J-EDI QA, a benchmark for understanding images of deep-sea organisms using a multimodal large language model (LLM). The benchmark is comprised of 100 images, accompanied by questions and answers with four options by JAMSTEC researchers for each image. The QA pairs are provided in Japanese, and the benchmark assesses the ability to understand deep-sea species in Japanese. In the evaluation presented in this paper, OpenAI o1 achieved a 50% correct response rate. This result indicates that even with the capabilities of state-of-the-art models as of December 2024, deep-sea species comprehension is not yet at an expert level. Further advances in deep-sea species-specific LLMs are therefore required.
Vision Language Models (VLMs) can be trained more efficiently if training sets can be reduced in size. Recent work has shown the benefits of masking text during VLM training using a variety of approaches: truncation, random masking, block masking and syntax masking. In this paper, we show that the best masking strategy changes over training epochs and that, given sufficient training epochs, word frequency information is what you need to achieve the best performance. Experiments on a large range of data sets demonstrate the advantages of our approach, called Contrastive Language-Image Pre-training with word Frequency Masking (CLIPF). The benefits are particularly evident as the number of input tokens decreases. We analyze the impact of CLIPF vs. other masking approaches on word frequency balance and discuss the apparently critical contribution of CLIPF in maintaining word frequency balance across POS categories.
Problem: Pancreas radiological imaging is challenging due to the small size, blurred boundaries, and variability of shape and position of the organ among patients. Goal: In this work we present MiniGPT-Pancreas, a Multimodal Large Language Model (MLLM), as an interactive chatbot to support clinicians in pancreas cancer diagnosis by integrating visual and textual information. Methods: MiniGPT-v2, a general-purpose MLLM, was fine-tuned in a cascaded way for pancreas detection, tumor classification, and tumor detection with multimodal prompts combining questions and computed tomography scans from the National Institute of Health (NIH), and Medical Segmentation Decathlon (MSD) datasets. The AbdomenCT-1k dataset was used to detect the liver, spleen, kidney, and pancreas. Results: MiniGPT-Pancreas achieved an Intersection over Union (IoU) of 0.595 and 0.550 for the detection of pancreas on NIH and MSD datasets, respectively. For the pancreas cancer classification task on the MSD dataset, accuracy, precision, and recall were 0.876, 0.874, and 0.878, respectively. When evaluating MiniGPT-Pancreas on the AbdomenCT-1k dataset for multi-organ detection, the IoU was 0.8399 for the liver, 0.722 for the kidney, 0.705 for the spleen, and 0.497 for the pancreas. For the pancreas tumor detection task, the IoU score was 0.168 on the MSD dataset. Conclusions: MiniGPT-Pancreas represents a promising solution to support clinicians in the classification of pancreas images with pancreas tumors. Future research is needed to improve the score on the detection task, especially for pancreas tumors.
We present ARCAS (Automated Root Cause Analysis System), a diagnostic platform based on a Domain Specific Language (DSL) built for fast diagnostic implementation and low learning curve. Arcas is composed of a constellation of automated troubleshooting guides (Auto-TSGs) that can execute in parallel to detect issues using product telemetry and apply mitigation in near-real-time. The DSL is tailored specifically to ensure that subject matter experts can deliver highly curated and relevant Auto-TSGs in a short time without having to understand how they will interact with the rest of the diagnostic platform, thus reducing time-to-mitigate and saving crucial engineering cycles when they matter most. This contrasts with platforms like Datadog and New Relic, which primarily focus on monitoring and require manual intervention for mitigation. ARCAS uses a Large Language Model (LLM) to prioritize Auto-TSGs outputs and take appropriate actions, thus suppressing the costly requirement of understanding the general behavior of the system. We explain the key concepts behind ARCAS and demonstrate how it has been successfully used for multiple products across Azure Synapse Analytics and Microsoft Fabric Synapse Data Warehouse.
We argue that the Declarative Self-improving Python (DSPy) optimizers are a way to align the large language model (LLM) prompts and their evaluations to the human annotations. We present a comparative analysis of five teleprompter algorithms, namely, Cooperative Prompt Optimization (COPRO), Multi-Stage Instruction Prompt Optimization (MIPRO), BootstrapFewShot, BootstrapFewShot with Optuna, and K-Nearest Neighbor Few Shot, within the DSPy framework with respect to their ability to align with human evaluations. As a concrete example, we focus on optimizing the prompt to align hallucination detection (using LLM as a judge) to human annotated ground truth labels for a publicly available benchmark dataset. Our experiments demonstrate that optimized prompts can outperform various benchmark methods to detect hallucination, and certain telemprompters outperform the others in at least these experiments.
Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing methods primarily design sophisticated instructions for the LLM to follow, or rely on multiple iterations, which could hinder the performance and efficiency of jailbreaks. In this work, we propose a novel jailbreak paradigm, Simple Assistive Task Linkage (SATA), which can effectively circumvent LLM safeguards and elicit harmful responses. Specifically, SATA first masks harmful keywords within a malicious query to generate a relatively benign query containing one or multiple [MASK] special tokens. It then employs a simple assistive task such as a masked language model task or an element lookup by position task to encode the semantics of the masked keywords. Finally, SATA links the assistive task with the masked query to jointly perform the jailbreak. Extensive experiments show that SATA achieves state-of-the-art performance and outperforms baselines by a large margin. Specifically, on AdvBench dataset, with mask language model (MLM) assistive task, SATA achieves an overall attack success rate (ASR) of 85% and harmful score (HS) of 4.57, and with element lookup by position (ELP) assistive task, SATA attains an overall ASR of 76% and HS of 4.43.
We introduce CLOB, a novel continual learning (CL) paradigm wherein a large language model (LLM) is regarded as a black box. Learning is done incrementally via only verbal prompting. CLOB does not fine-tune any part of the LLM or add any trainable parameters to it. It is particularly suitable for LLMs that are accessible via APIs. We also propose a new CL technique, called CIS, based on incremental summarization that also overcomes the LLM's input length limit. Experiments show CIS outperforms baselines by a very large margin.
The integration of multi-omic data is pivotal for understanding complex diseases, but its high dimensionality and noise present significant challenges. Graph Neural Networks (GNNs) offer a robust framework for analyzing large-scale signaling pathways and protein-protein interaction networks, yet they face limitations in expressivity when capturing intricate biological relationships. To address this, we propose Graph Sequence Language Model (GraphSeqLM), a framework that enhances GNNs with biological sequence embeddings generated by Large Language Models (LLMs). These embeddings encode structural and biological properties of DNA, RNA, and proteins, augmenting GNNs with enriched features for analyzing sample-specific multi-omic data. By integrating topological, sequence-derived, and biological information, GraphSeqLM demonstrates superior predictive accuracy and outperforms existing methods, paving the way for more effective multi-omic data integration in precision medicine.
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-modal tool-usage data and tunes a vision-language model (VLM) as the controller for powerful tool-usage reasoning. To preserve the data quality, we prompt the GPT-4o mini model to generate queries, files, and trajectories, followed by query-file and trajectory verifiers. Based on the data synthesis pipeline, we collect the MM-Traj dataset that contains 20K tasks with trajectories of tool usage. Then, we develop the T3-Agent via \underline{T}rajectory \underline{T}uning on VLMs for \underline{T}ool usage using MM-Traj. Evaluations on the GTA and GAIA benchmarks show that the T3-Agent consistently achieves improvements on two popular VLMs: MiniCPM-V-8.5B and {Qwen2-VL-7B}, which outperforms untrained VLMs by $20\%$, showing the effectiveness of the proposed data synthesis pipeline, leading to high-quality data for tool-usage capabilities.
The rapid development of large language models (LLMs) has transformed many industries, including healthcare. However, previous medical LLMs have largely focused on leveraging general medical knowledge to provide responses, without accounting for patient variability and lacking true personalization at the individual level. To address this, we propose a novel method called personalized medical language model (PMLM), which explores and optimizes personalized LLMs through recommendation systems and reinforcement learning (RL). Specifically, by utilizing self-informed and peer-informed personalization, PMLM captures changes in behaviors and preferences to design initial personalized prompts tailored to individual needs. We further refine these initial personalized prompts through RL, ultimately enhancing the precision of LLM guidance. Notably, the personalized prompt are hard prompt, which grants PMLM high adaptability and reusability, allowing it to directly leverage high-quality proprietary LLMs. We evaluate PMLM using real-world obstetrics and gynecology data, and the experimental results demonstrate that PMLM achieves personalized responses, and it provides more refined and individualized services, offering a potential way for personalized medical LLMs.
Background: Recent advances in large language models highlight the need for high-quality multilingual medical datasets. While Japan leads globally in CT scanner deployment and utilization, the lack of large-scale Japanese radiology datasets has hindered the development of specialized language models for medical imaging analysis. Objective: To develop a comprehensive Japanese CT report dataset through machine translation and establish a specialized language model for structured finding classification. Additionally, to create a rigorously validated evaluation dataset through expert radiologist review. Methods: We translated the CT-RATE dataset (24,283 CT reports from 21,304 patients) into Japanese using GPT-4o mini. The training dataset consisted of 22,778 machine-translated reports, while the validation dataset included 150 radiologist-revised reports. We developed CT-BERT-JPN based on "tohoku-nlp/bert-base-japanese-v3" architecture for extracting 18 structured findings from Japanese radiology reports. Results: Translation metrics showed strong performance with BLEU scores of 0.731 and 0.690, and ROUGE scores ranging from 0.770 to 0.876 for Findings and from 0.748 to 0.857 for Impression sections. CT-BERT-JPN demonstrated superior performance compared to GPT-4o in 11 out of 18 conditions, including lymphadenopathy (+14.2%), interlobular septal thickening (+10.9%), and atelectasis (+7.4%). The model maintained F1 scores exceeding 0.95 in 14 out of 18 conditions and achieved perfect scores in four conditions. Conclusions: Our study establishes a robust Japanese CT report dataset and demonstrates the effectiveness of a specialized language model for structured finding classification. The hybrid approach of machine translation and expert validation enables the creation of large-scale medical datasets while maintaining high quality.
Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these tasks, the impact of different memory structures across tasks remains insufficiently explored. This paper investigates how memory structures and memory retrieval methods affect the performance of LLM-based agents. Specifically, we evaluate four types of memory structures, including chunks, knowledge triples, atomic facts, and summaries, along with mixed memory that combines these components. In addition, we evaluate three widely used memory retrieval methods: single-step retrieval, reranking, and iterative retrieval. Extensive experiments conducted across four tasks and six datasets yield the following key insights: (1) Different memory structures offer distinct advantages, enabling them to be tailored to specific tasks; (2) Mixed memory structures demonstrate remarkable resilience in noisy environments; (3) Iterative retrieval consistently outperforms other methods across various scenarios. Our investigation aims to inspire further research into the design of memory systems for LLM-based agents.
The Harmonized Tariff System (HTS) classification industry, essential to e-commerce and international trade, currently lacks standardized benchmarks for evaluating the effectiveness of classification solutions. This study establishes and tests a benchmark framework for imports to the United States, inspired by the benchmarking approaches used in language model evaluation, to systematically compare prominent HTS classification tools. The framework assesses key metrics--such as speed, accuracy, rationality, and HTS code alignment--to provide a comprehensive performance comparison. The study evaluates several industry-leading solutions, including those provided by Zonos, Tarifflo, Avalara, and WCO BACUDA, identifying each tool's strengths and limitations. Results highlight areas for industry-wide improvement and innovation, paving the way for more effective and standardized HTS classification solutions across the international trade and e-commerce sectors.
Conflict scholars have used rule-based approaches to extract information about political violence from news reports and texts. Recent Natural Language Processing developments move beyond rigid rule-based approaches. We review our recent ConfliBERT language model (Hu et al. 2022) to process political and violence related texts. The model can be used to extract actor and action classifications from texts about political conflict. When fine-tuned, results show that ConfliBERT has superior performance in accuracy, precision and recall over other large language models (LLM) like Google's Gemma 2 (9B), Meta's Llama 3.1 (7B), and Alibaba's Qwen 2.5 (14B) within its relevant domains. It is also hundreds of times faster than these more generalist LLMs. These results are illustrated using texts from the BBC, re3d, and the Global Terrorism Dataset (GTD).
Recent advances in machine learning, particularly Large Language Models (LLMs) such as BERT and GPT, provide rich contextual embeddings that improve text representation. However, current document clustering approaches often ignore the deeper relationships between named entities (NEs) and the potential of LLM embeddings. This paper proposes a novel approach that integrates Named Entity Recognition (NER) and LLM embeddings within a graph-based framework for document clustering. The method builds a graph with nodes representing documents and edges weighted by named entity similarity, optimized using a graph-convolutional network (GCN). This ensures a more effective grouping of semantically related documents. Experimental results indicate that our approach outperforms conventional co-occurrence-based methods in clustering, notably for documents rich in named entities.
When using agent-task datasets to enhance agent capabilities for Large Language Models (LLMs), current methodologies often treat all tokens within a sample equally. However, we argue that tokens serving different roles - specifically, reasoning tokens versus boilerplate tokens (e.g., those governing output format) - differ significantly in importance and learning complexity, necessitating their disentanglement and distinct treatment. To address this, we propose a novel Shuffle-Aware Discriminator (SHAD) for adaptive token discrimination. SHAD classifies tokens by exploiting predictability differences observed after shuffling input-output combinations across samples: boilerplate tokens, due to their repetitive nature among samples, maintain predictability, whereas reasoning tokens do not. Using SHAD, we propose the Reasoning-highlighted Fine-Tuning (RFT) method, which adaptively emphasizes reasoning tokens during fine-tuning, yielding notable performance gains over common Supervised Fine-Tuning (SFT).
Large Language Models (LLMs) have shown exciting performance in listwise passage ranking. Due to the limited input length, existing methods often adopt the sliding window strategy. Such a strategy, though effective, is inefficient as it involves repetitive and serialized processing, which usually re-evaluates relevant passages multiple times. As a result, it incurs redundant API costs, which are proportional to the number of inference tokens. The development of long-context LLMs enables the full ranking of all passages within a single inference, avoiding redundant API costs. In this paper, we conduct a comprehensive study of long-context LLMs for ranking tasks in terms of efficiency and effectiveness. Surprisingly, our experiments reveal that full ranking with long-context LLMs can deliver superior performance in the supervised fine-tuning setting with a huge efficiency improvement. Furthermore, we identify two limitations of fine-tuning the full ranking model based on existing methods: (1) sliding window strategy fails to produce a full ranking list as a training label, and (2) the language modeling loss cannot emphasize top-ranked passage IDs in the label. To alleviate these issues, we propose a new complete listwise label construction approach and a novel importance-aware learning objective for full ranking. Experiments show the superior performance of our method over baselines. Our codes are available at \url{https://github.com/8421BCD/fullrank}.
We study the problem of aligning large language models (LLMs) with human preference data. Contrastive preference optimization has shown promising results in aligning LLMs with available preference data by optimizing the implicit reward associated with the policy. However, the contrastive objective focuses mainly on the relative values of implicit rewards associated with two responses while ignoring their actual values, resulting in suboptimal alignment with human preferences. To address this limitation, we propose calibrated direct preference optimization (Cal-DPO), a simple yet effective algorithm. We show that substantial improvement in alignment with the given preferences can be achieved simply by calibrating the implicit reward to ensure that the learned implicit rewards are comparable in scale to the ground-truth rewards. We demonstrate the theoretical advantages of Cal-DPO over existing approaches. The results of our experiments on a variety of standard benchmarks show that Cal-DPO remarkably improves off-the-shelf methods.