Community Discussion on Open-Source LLMs for Chatbot Development
A discussion thread on the Hugging Face forums asks users which free or open-source AI models they currently utilize for chatbot development and their reasons for preference.
Top 5 models i can run with my hardware? No AI lobotomization
A user on the Hugging Face forums seeks recommendations for uncensored AI models capable of reasoning about complex topics, citing a preference for earlier versions of GPT-4 over current iterations.
llama.cpp b9847 release fixes Gemma E4B MTP FlashAttention
The llama.cpp project has released version b9847, which includes a fix for Gemma E4B MTP FlashAttention on CUDA and the removal of an unused template declaration.
How I'm using local models from real-world coding
The author shares a practical setup for using local large language models on modest hardware, specifically a laptop with 32GB of RAM and an NVIDIA RTX 4070 with 8GB VRAM. The core strategy involves running the Qwen3.6-35B-A3B model locally as a 'small coding agent' while offloading complex planning to a cloud-based GLM 5.2 instance.
A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents
The article documents how measurements from proprietary LLM evaluators can become invalid within weeks, introducing the EPC framework to detect such instability. It applies this diagnostic across eight experimental conditions, revealing that version-conditional instability makes single-snapshot evaluator studies unreliable.
The Hidden Cost of Resampling: How Imbalance Correction Degrades Probability Calibration in Tree Ensembles
This study evaluates the impact of resampling methods like SMOTE and random undersampling on probability calibration in tree ensembles, finding that while SMOTE's cost is small, undersampling severely degrades calibration.
How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD
This study evaluates the performance of open-weight large language models running on-premises for text-to-SQL tasks using a reproducible benchmark on the BIRD development split. It compares three model families across two generations while ablating specific accuracy-enhancing techniques to determine their actual value.
Fast Numbers, Slow Language: Bridging Quantitative and Qualitative Earnings Signals
The article introduces EarningsInOne, a new corpus aligning earnings news, conference call transcripts, and prices for the SP 1500 universe from 2022 to 2025. This resource bridges the gap between financial economists and NLP researchers by providing unified trading setups and evaluation metrics for both quantitative and qualitative signals.
Managing Map Cardinality in Automatic Disease Classification Mapping
The article introduces a novel method for automatic mapping between disease classification systems, such as ICD-9-CM and ICD-10-CM, that addresses the limitations of existing embedding-based approaches which often overlook complex one-to-many scenarios. By employing a blocking-and-matching pipeline inspired by entity resolution, the authors utilize large language models to identify valid mappings within candidate blocks.
Mandol: An Agglomerative Agent Memory System for Long-Term Conversations
Researchers propose Mandol, an agglomerative memory system designed to consolidate fragmented memory representations into a unified architecture for long-term conversational agents. This approach addresses the high latency and noise issues inherent in existing systems that rely on heterogeneous vector and graph databases.
Are Humans Evolved Instruction Followers? An Underlying Inductive Bias Enables Rapid Instructed Task Learning
This position paper argues that humans possess an evolved instruction-following bias, an innate inductive bias shaped by evolution to interpret and execute linguistic instructions. This cognitive feature enables rapid instructed task learning (RITL) and allows for the fast generalization of behavior from language.
Fund2Persona: Building Financial Advisor Personas from Fund Data
The authors propose Fund2Persona, a framework that grounds financial advisor personas in fund disclosures, holdings transitions, and manager commentary to address the difficulty of scaling consistent expertise in LLM systems. The system refines these personas through an agentic actor-scorer-patcher loop, moving beyond simple persona prompts that often drift toward generic recommendations.
Systematic Benchmark of Lightweight Hallucination Detection Across QA, Dialogue, and Summarisation
This paper benchmarks five lightweight, CPU-feasible hallucination detection methods to provide practical alternatives for resource-constrained researchers who cannot use GPU-intensive or proprietary solutions. The study evaluates ROUGE-L, semantic similarity, BERTScore, a FEVER-trained DeBERTa NLI detector, and an ensemble of similarity and NLI across the HaluEval benchmark's question answering, dialogue, and summarisation tasks.
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code LLMs
The authors introduce SrDetection, a unified framework for detecting data leakage in code large language models that operates in both gray-box and black-box settings. The method generates semantically equivalent variants of benchmark samples to identify cases where the original data is disproportionately easier for the model due to pre-training exposure.
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
The paper introduces Neural Procedural Memory (NPM), a training-free framework that enables Large Language Model agents to utilize implicit activation steering for procedural memory instead of relying on explicit textual instructions. By distilling skills from historical experiences into steering vectors, NPM directly activates task-relevant neural mechanisms to guide execution.
Revealing the Technology Development of Natural Language Processing: A Scientific Entity-Centric Perspective
This study analyzes the development of technologies in Natural Language Processing (NLP) from an entity-centric perspective, extracting methods, datasets, metrics, and tools to measure their impact via co-occurrence networks. The research reveals that while pre-trained language models like BERT and Transformer have become mainstream, the average number of entities per paper is increasing, indicating a growing knowledge burden for researchers.
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers
The authors propose MATCH, a framework that augments sparsified attention mechanisms with dynamically integrated in-context information to address the scalability bottlenecks of traditional attention in long-context scenarios.
Smooth Scaling Laws Hide Stepwise Token Learning
This study presents a token-level framework that decomposes language model scaling laws into localized learning events of individual contextualized tokens, challenging the view that heavy-tailed pattern difficulty is the sole cause.
Exploring Motivations for Algorithm Mention in NLP: A Deep Learning Approach
This study proposes a sentence-level framework to identify, analyze, and trace the evolution of motivations for mentioning algorithms in academic papers, using natural language processing as a case study. The researchers classify these motivations using pretrained models and data augmentation, revealing that deep learning models outperform traditional machine learning approaches.
KbSD: Knowledge Boundary aware Self-Distillation for Behavioral Calibration
The authors propose KbSD, a framework that addresses reward sparsity in agentic search by using dense token-level supervision and quadrant-adaptive optimization to calibrate when models should trust parametric memory versus retrieved evidence. This approach utilizes an information-asymmetric self-distillation process where a hint-augmented teacher generates calibrated reasoning demonstrations for a student model without requiring a larger external model.