TS-Reasoner is a domain-oriented agent using LLMs, computational tools, and error feedback for multi-step time series inference, showing better performance than general LLMs on understanding and reasoning benchmarks.
Domain specialization as the key to make large language models disruptive: A comprehensive survey
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Experiments across code LLMs show no-review collapses fastest, human-gated filters slow collapse, and AI self-gates lose effect over time, degenerating to ungated self-training under self-confirming acceptance as proven via gated distributional reweighting and spectral analysis.
A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.
PIE creates predicate-aware embeddings by weighting subjectless triples and DRSD distills LLM reasoning into an SLM while decoupling confidence from rationales to improve entity alignment and enable human-in-the-loop verification.
LLMs override explicit source evidence with internal knowledge when modeling business processes, creating a measurable reliability risk in analytical tasks.
RAG is more effective and cost-efficient than fine-tuning for industrial QA adaptation on automotive datasets.
Fine-tuned LLaMA 3.1-8B variants for the energy sector outperform the base model on domain QA benchmarks, with LoRA delivering similar gains at lower training cost.
citing papers explorer
-
TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
TS-Reasoner is a domain-oriented agent using LLMs, computational tools, and error feedback for multi-step time series inference, showing better performance than general LLMs on understanding and reasoning benchmarks.
-
When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
Experiments across code LLMs show no-review collapses fastest, human-gated filters slow collapse, and AI self-gates lose effect over time, degenerating to ungated self-training under self-confirming acceptance as proven via gated distributional reweighting and spectral analysis.
-
ToolRL: Reward is All Tool Learning Needs
A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.
-
Predicate Importance Estimation and Decoupled Rationale-Score Distillation for Entity Alignment
PIE creates predicate-aware embeddings by weighting subjectless triples and DRSD distills LLM reasoning into an SLM while decoupling confidence from rationales to improve entity alignment and enable human-in-the-loop verification.
-
Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling
LLMs override explicit source evidence with internal knowledge when modeling business processes, creating a measurable reliability risk in analytical tasks.
-
Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications
RAG is more effective and cost-efficient than fine-tuning for industrial QA adaptation on automotive datasets.
-
Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector
Fine-tuned LLaMA 3.1-8B variants for the energy sector outperform the base model on domain QA benchmarks, with LoRA delivering similar gains at lower training cost.