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
How to Analyze and Optimize Your LLMs in 3 StepsTowards Data Scienceon September 11, 2025 at 2:30 pm Learn to enhance your LLMs with my 3 step process, inspecting, improving and iterating on your LLMs
The post How to Analyze and Optimize Your LLMs in 3 Steps appeared first on Towards Data Science.
Learn to enhance your LLMs with my 3 step process, inspecting, improving and iterating on your LLMs
The post How to Analyze and Optimize Your LLMs in 3 Steps appeared first on Towards Data Science. Read More
Yext Scout Guides Brands Through AI Search ChallengesAI Newson September 11, 2025 at 2:19 pm Customers are discovering brands and learning about products and services in new ways from traditional search to AI search, to AI agents and more, the discovery journey has completely changed, and brands need to adapt to the new paradigm. Launched earlier this year, Yext Scout is an AI search and competitive intelligence agent that’s designed
The post Yext Scout Guides Brands Through AI Search Challenges appeared first on AI News.
Customers are discovering brands and learning about products and services in new ways from traditional search to AI search, to AI agents and more, the discovery journey has completely changed, and brands need to adapt to the new paradigm. Launched earlier this year, Yext Scout is an AI search and competitive intelligence agent that’s designed
The post Yext Scout Guides Brands Through AI Search Challenges appeared first on AI News. Read More
VMware nods to AI but looks to long-termAI Newson September 11, 2025 at 3:44 pm Owner of VMware, Broadcom, announced that its VMware Cloud Foundation platform is now AI native at the VMware Explore conference a few weeks ago. It was the latest move by the company to keep up to speed with the rest of the technology industry’s wide and rapid adoption of large language models, yet came as
The post VMware nods to AI but looks to long-term appeared first on AI News.
Owner of VMware, Broadcom, announced that its VMware Cloud Foundation platform is now AI native at the VMware Explore conference a few weeks ago. It was the latest move by the company to keep up to speed with the rest of the technology industry’s wide and rapid adoption of large language models, yet came as
The post VMware nods to AI but looks to long-term appeared first on AI News. Read More
Fighting Back Against Attacks in Federated Learning Towards Data Scienceon September 10, 2025 at 5:00 pm Lessons from a multi-node simulator
The post Fighting Back Against Attacks in Federated Learning appeared first on Towards Data Science.
Lessons from a multi-node simulator
The post Fighting Back Against Attacks in Federated Learning appeared first on Towards Data Science. Read More
When A Difference Actually Makes A DifferenceTowards Data Scienceon September 10, 2025 at 3:30 pm Bite-Sized Analytics for Business Decision-Makers (1)
The post When A Difference Actually Makes A Difference appeared first on Towards Data Science.
Bite-Sized Analytics for Business Decision-Makers (1)
The post When A Difference Actually Makes A Difference appeared first on Towards Data Science. Read More
