The Download: America’s gun crisis, and how AI video models workMIT Technology Reviewon September 12, 2025 at 12:10 pm This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. We can’t “make American children healthy again” without tackling the gun crisis This week, the Trump administration released a strategy for improving the health and well-being of American children. The report was titled—you…
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. We can’t “make American children healthy again” without tackling the gun crisis This week, the Trump administration released a strategy for improving the health and well-being of American children. The report was titled—you… Read More
If we use AI to do our work – what is our job, then?Towards Data Scienceon September 12, 2025 at 3:31 pm Images. Text. Audio. There’s no modality that is not handled by AI. And AI systems reach even further, planning advertisement and marketing campaigns, automating social media postings, … Most of this was unthinkable a mere ten years ago. But then, the first machine learning-driven algorithms did their initial steps: out of the research labs, into
The post If we use AI to do our work – what is our job, then? appeared first on Towards Data Science.
Images. Text. Audio. There’s no modality that is not handled by AI. And AI systems reach even further, planning advertisement and marketing campaigns, automating social media postings, … Most of this was unthinkable a mere ten years ago. But then, the first machine learning-driven algorithms did their initial steps: out of the research labs, into
The post If we use AI to do our work – what is our job, then? appeared first on Towards Data Science. Read More
Generalists Can Also Dig DeepTowards Data Scienceon September 12, 2025 at 1:32 pm Ida Silfverskiöld on AI agents, RAG, evals, and what design choice ended up mattering more than expected
The post Generalists Can Also Dig Deep appeared first on Towards Data Science.
Ida Silfverskiöld on AI agents, RAG, evals, and what design choice ended up mattering more than expected
The post Generalists Can Also Dig Deep appeared first on Towards Data Science. Read More
Enhancing Few-Shot Transfer Learning with Optimized Multi-Task Prompt Tuning through Modular Prompt Compositioncs.AI updates on arXiv.orgon September 12, 2025 at 4:00 am arXiv:2408.13227v2 Announce Type: replace
Abstract: In recent years, multi-task prompt tuning has garnered considerable attention for its inherent modularity and potential to enhance parameter-efficient transfer learning across diverse tasks. This paper aims to analyze and improve the performance of multiple tasks by facilitating the transfer of knowledge between their corresponding prompts in a multi-task setting. Our proposed approach decomposes the prompt for each target task into a combination of shared prompts (source prompts) and a task-specific prompt (private prompt). During training, the source prompts undergo fine-tuning and are integrated with the private prompt to drive the target prompt for each task. We present and compare multiple methods for combining source prompts to construct the target prompt, analyzing the roles of both source and private prompts within each method. We investigate their contributions to task performance and offer flexible, adjustable configurations based on these insights to optimize performance. Our empirical findings clearly showcase improvements in accuracy and robustness compared to the conventional practice of prompt tuning and related works. Notably, our results substantially outperform other methods in the field in few-shot settings, demonstrating superior performance in various tasks across GLUE benchmark, among other tasks. This achievement is attained with a significantly reduced amount of training data, making our method a promising one for few-shot settings.
arXiv:2408.13227v2 Announce Type: replace
Abstract: In recent years, multi-task prompt tuning has garnered considerable attention for its inherent modularity and potential to enhance parameter-efficient transfer learning across diverse tasks. This paper aims to analyze and improve the performance of multiple tasks by facilitating the transfer of knowledge between their corresponding prompts in a multi-task setting. Our proposed approach decomposes the prompt for each target task into a combination of shared prompts (source prompts) and a task-specific prompt (private prompt). During training, the source prompts undergo fine-tuning and are integrated with the private prompt to drive the target prompt for each task. We present and compare multiple methods for combining source prompts to construct the target prompt, analyzing the roles of both source and private prompts within each method. We investigate their contributions to task performance and offer flexible, adjustable configurations based on these insights to optimize performance. Our empirical findings clearly showcase improvements in accuracy and robustness compared to the conventional practice of prompt tuning and related works. Notably, our results substantially outperform other methods in the field in few-shot settings, demonstrating superior performance in various tasks across GLUE benchmark, among other tasks. This achievement is attained with a significantly reduced amount of training data, making our method a promising one for few-shot settings. Read More
A modified RIME algorithm with covariance learning and diversity enhancement for numerical optimizationcs.AI updates on arXiv.orgon September 12, 2025 at 4:00 am arXiv:2509.09529v1 Announce Type: cross
Abstract: Metaheuristics are widely applied for their ability to provide more efficient solutions. The RIME algorithm is a recently proposed physical-based metaheuristic algorithm with certain advantages. However, it suffers from rapid loss of population diversity during optimization and is prone to fall into local optima, leading to unbalanced exploitation and exploration. To address the shortcomings of RIME, this paper proposes a modified RIME with covariance learning and diversity enhancement (MRIME-CD). The algorithm applies three strategies to improve the optimization capability. First, a covariance learning strategy is introduced in the soft-rime search stage to increase the population diversity and balance the over-exploitation ability of RIME through the bootstrapping effect of dominant populations. Second, in order to moderate the tendency of RIME population to approach the optimal individual in the early search stage, an average bootstrapping strategy is introduced into the hard-rime puncture mechanism, which guides the population search through the weighted position of the dominant populations, thus enhancing the global search ability of RIME in the early stage. Finally, a new stagnation indicator is proposed, and a stochastic covariance learning strategy is used to update the stagnant individuals in the population when the algorithm gets stagnant, thus enhancing the ability to jump out of the local optimal solution. The proposed MRIME-CD algorithm is subjected to a series of validations on the CEC2017 test set, the CEC2022 test set, and the experimental results are analyzed using the Friedman test, the Wilcoxon rank sum test, and the Kruskal Wallis test. The results show that MRIME-CD can effectively improve the performance of basic RIME and has obvious superiorities in terms of solution accuracy, convergence speed and stability.
arXiv:2509.09529v1 Announce Type: cross
Abstract: Metaheuristics are widely applied for their ability to provide more efficient solutions. The RIME algorithm is a recently proposed physical-based metaheuristic algorithm with certain advantages. However, it suffers from rapid loss of population diversity during optimization and is prone to fall into local optima, leading to unbalanced exploitation and exploration. To address the shortcomings of RIME, this paper proposes a modified RIME with covariance learning and diversity enhancement (MRIME-CD). The algorithm applies three strategies to improve the optimization capability. First, a covariance learning strategy is introduced in the soft-rime search stage to increase the population diversity and balance the over-exploitation ability of RIME through the bootstrapping effect of dominant populations. Second, in order to moderate the tendency of RIME population to approach the optimal individual in the early search stage, an average bootstrapping strategy is introduced into the hard-rime puncture mechanism, which guides the population search through the weighted position of the dominant populations, thus enhancing the global search ability of RIME in the early stage. Finally, a new stagnation indicator is proposed, and a stochastic covariance learning strategy is used to update the stagnant individuals in the population when the algorithm gets stagnant, thus enhancing the ability to jump out of the local optimal solution. The proposed MRIME-CD algorithm is subjected to a series of validations on the CEC2017 test set, the CEC2022 test set, and the experimental results are analyzed using the Friedman test, the Wilcoxon rank sum test, and the Kruskal Wallis test. The results show that MRIME-CD can effectively improve the performance of basic RIME and has obvious superiorities in terms of solution accuracy, convergence speed and stability. Read More
EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMscs.AI updates on arXiv.orgon September 12, 2025 at 4:00 am arXiv:2509.09174v1 Announce Type: cross
Abstract: Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning capabilities. We hypothesize that this limitation arises because current training paradigms for SLLMs fail to bridge the acoustic-semantic gap in the feature representation space. To address this issue, we propose EchoX, which leverages semantic representations and dynamically generates speech training targets. This approach integrates both acoustic and semantic learning, enabling EchoX to preserve strong reasoning abilities as a speech LLM. Experimental results demonstrate that EchoX, with about six thousand hours of training data, achieves advanced performance on multiple knowledge-based question-answering benchmarks. The project is available at https://github.com/FreedomIntelligence/EchoX.
arXiv:2509.09174v1 Announce Type: cross
Abstract: Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning capabilities. We hypothesize that this limitation arises because current training paradigms for SLLMs fail to bridge the acoustic-semantic gap in the feature representation space. To address this issue, we propose EchoX, which leverages semantic representations and dynamically generates speech training targets. This approach integrates both acoustic and semantic learning, enabling EchoX to preserve strong reasoning abilities as a speech LLM. Experimental results demonstrate that EchoX, with about six thousand hours of training data, achieves advanced performance on multiple knowledge-based question-answering benchmarks. The project is available at https://github.com/FreedomIntelligence/EchoX. Read More
Meta-Semantics Augmented Few-Shot Relational Learningcs.AI updates on arXiv.orgon September 11, 2025 at 4:00 am arXiv:2505.05684v2 Announce Type: replace
Abstract: Few-shot relational learning on knowledge graph (KGs) aims to perform reasoning over relations with only a few training examples. While existing methods have primarily focused on leveraging specific relational information, rich semantics inherent in KGs have been largely overlooked. To address this critical gap, we propose a novel prompted meta-learning (PromptMeta) framework that seamlessly integrates meta-semantics with relational information for few-shot relational learning. PromptMeta has two key innovations: (1) a Meta-Semantic Prompt (MSP) pool that learns and consolidates high-level meta-semantics, enabling effective knowledge transfer and adaptation to rare and newly emerging relations; and (2) a learnable fusion token that dynamically combines meta-semantics with task-specific relational information tailored to different few-shot tasks. Both components are optimized jointly with model parameters within a meta-learning framework. Extensive experiments and analyses on two real-world KG datasets demonstrate the effectiveness of PromptMeta in adapting to new relations with limited data.
arXiv:2505.05684v2 Announce Type: replace
Abstract: Few-shot relational learning on knowledge graph (KGs) aims to perform reasoning over relations with only a few training examples. While existing methods have primarily focused on leveraging specific relational information, rich semantics inherent in KGs have been largely overlooked. To address this critical gap, we propose a novel prompted meta-learning (PromptMeta) framework that seamlessly integrates meta-semantics with relational information for few-shot relational learning. PromptMeta has two key innovations: (1) a Meta-Semantic Prompt (MSP) pool that learns and consolidates high-level meta-semantics, enabling effective knowledge transfer and adaptation to rare and newly emerging relations; and (2) a learnable fusion token that dynamically combines meta-semantics with task-specific relational information tailored to different few-shot tasks. Both components are optimized jointly with model parameters within a meta-learning framework. Extensive experiments and analyses on two real-world KG datasets demonstrate the effectiveness of PromptMeta in adapting to new relations with limited data. Read More
Automatic Detection of Inauthentic Templated Responses in English Language Assessmentscs.AI updates on arXiv.orgon September 11, 2025 at 4:00 am arXiv:2509.08355v1 Announce Type: cross
Abstract: In high-stakes English Language Assessments, low-skill test takers may employ memorized materials called “templates” on essay questions to “game” or fool the automated scoring system. In this study, we introduce the automated detection of inauthentic, templated responses (AuDITR) task, describe a machine learning-based approach to this task and illustrate the importance of regularly updating these models in production.
arXiv:2509.08355v1 Announce Type: cross
Abstract: In high-stakes English Language Assessments, low-skill test takers may employ memorized materials called “templates” on essay questions to “game” or fool the automated scoring system. In this study, we introduce the automated detection of inauthentic, templated responses (AuDITR) task, describe a machine learning-based approach to this task and illustrate the importance of regularly updating these models in production. Read More
Combined-distance-based score function of cognitive fuzzy sets and its application in lung cancer pain evaluationcs.AI updates on arXiv.orgon September 11, 2025 at 4:00 am arXiv:2509.08239v1 Announce Type: cross
Abstract: In decision making, the cognitive fuzzy set (CFS) is a useful tool in expressing experts’ complex assessments of alternatives. The distance of CFS, which plays an important role in decision analyses, is necessary when the CFS is applied in solving practical issues. However, as far as we know, the studies on the distance of CFS are few, and the current Minkowski distance of CFS ignores the hesitancy degree of CFS, which might cause errors. To fill the gap of the studies on the distance of CFS, because of the practicality of the Hausdorff distance, this paper proposes the improved cognitive fuzzy Minkowski (CF-IM) distance and the cognitive fuzzy Hausdorff (CF-H) distance to enrich the studies on the distance of CFS. It is found that the anti-perturbation ability of the CF-H distance is stronger than that of the CF-IM distance, but the information utilization of the CF-IM distance is higher than that of the CF-H distance. To balance the anti-perturbation ability and information utilization of the CF-IM distance and CF-H distance, the cognitive fuzzy combined (CF-C) distance is proposed by establishing the linear combination of the CF-IM distance and CF-H distance. Based on the CF-C distance, a combined-distanced-based score function of CFS is proposed to compare CFSs. The proposed score function is employed in lung cancer pain evaluation issues. The sensitivity and comparison analyses demonstrate the reliability and advantages of the proposed methods.
arXiv:2509.08239v1 Announce Type: cross
Abstract: In decision making, the cognitive fuzzy set (CFS) is a useful tool in expressing experts’ complex assessments of alternatives. The distance of CFS, which plays an important role in decision analyses, is necessary when the CFS is applied in solving practical issues. However, as far as we know, the studies on the distance of CFS are few, and the current Minkowski distance of CFS ignores the hesitancy degree of CFS, which might cause errors. To fill the gap of the studies on the distance of CFS, because of the practicality of the Hausdorff distance, this paper proposes the improved cognitive fuzzy Minkowski (CF-IM) distance and the cognitive fuzzy Hausdorff (CF-H) distance to enrich the studies on the distance of CFS. It is found that the anti-perturbation ability of the CF-H distance is stronger than that of the CF-IM distance, but the information utilization of the CF-IM distance is higher than that of the CF-H distance. To balance the anti-perturbation ability and information utilization of the CF-IM distance and CF-H distance, the cognitive fuzzy combined (CF-C) distance is proposed by establishing the linear combination of the CF-IM distance and CF-H distance. Based on the CF-C distance, a combined-distanced-based score function of CFS is proposed to compare CFSs. The proposed score function is employed in lung cancer pain evaluation issues. The sensitivity and comparison analyses demonstrate the reliability and advantages of the proposed methods. Read More
Low-Resource Fine-Tuning for Multi-Task Structured Information Extraction with a Billion-Parameter Instruction-Tuned Modelcs.AI updates on arXiv.orgon September 11, 2025 at 4:00 am arXiv:2509.08381v1 Announce Type: cross
Abstract: Deploying large language models (LLMs) for structured data extraction in domains such as financial compliance reporting, legal document analytics, and multilingual knowledge base construction is often impractical for smaller teams due to the high cost of running large architectures and the difficulty of preparing large, high-quality datasets. Most recent instruction-tuning studies focus on seven-billion-parameter or larger models, leaving limited evidence on whether much smaller models can work reliably under low-resource, multi-task conditions. This work presents ETLCH, a billion-parameter LLaMA-based model fine-tuned with low-rank adaptation on only a few hundred to one thousand samples per task for JSON extraction, knowledge graph extraction, and named entity recognition. Despite its small scale, ETLCH outperforms strong baselines across most evaluation metrics, with substantial gains observed even at the lowest data scale. These findings demonstrate that well-tuned small models can deliver stable and accurate structured outputs at a fraction of the computational cost, enabling cost-effective and reliable information extraction pipelines in resource-constrained environments.
arXiv:2509.08381v1 Announce Type: cross
Abstract: Deploying large language models (LLMs) for structured data extraction in domains such as financial compliance reporting, legal document analytics, and multilingual knowledge base construction is often impractical for smaller teams due to the high cost of running large architectures and the difficulty of preparing large, high-quality datasets. Most recent instruction-tuning studies focus on seven-billion-parameter or larger models, leaving limited evidence on whether much smaller models can work reliably under low-resource, multi-task conditions. This work presents ETLCH, a billion-parameter LLaMA-based model fine-tuned with low-rank adaptation on only a few hundred to one thousand samples per task for JSON extraction, knowledge graph extraction, and named entity recognition. Despite its small scale, ETLCH outperforms strong baselines across most evaluation metrics, with substantial gains observed even at the lowest data scale. These findings demonstrate that well-tuned small models can deliver stable and accurate structured outputs at a fraction of the computational cost, enabling cost-effective and reliable information extraction pipelines in resource-constrained environments. Read More