Small Language Models
PulseAugur coverage of Small Language Models — every cluster mentioning Small Language Models across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Small language models show limited self-correction ability
A new research paper investigates the self-correction abilities of small language models (SLMs), finding that they struggle to improve their reasoning even when provided with correct answers and hints. The study develop…
-
Research: SLM outputs often reflect prompt artifacts, not psychology
A new research paper reveals that the outputs from small language models (SLMs) when used for psychometric assessments often reflect prompt artifacts rather than genuine psychological traits. The study analyzed 13 open-…
-
RAG research focuses on cost, intent, and chunking for better AI retrieval
Researchers are developing new methods to optimize Retrieval-Augmented Generation (RAG) systems for efficiency and accuracy. One approach, Cost-Aware RAG (CA-RAG), dynamically routes queries to different retrieval depth…
-
Small language models outperform LLMs in multilingual citation detection
Researchers have developed a new multilingual corpus, MCN, to address citation needed detection (CND) for lower-resource languages on Wikipedia. Their study demonstrates that small language models (SLMs) fine-tuned with…
-
HARNESS-LM trains compact models for faster sponsored search retrieval
Researchers have developed HARNESS-LM (HLM), a novel three-phase training framework designed to transfer the capabilities of large language models into compact, efficient models for sponsored search retrieval. This meth…
-
New benchmark dataset DeEscalWild trains small language models for police de-escalation
Researchers have developed DeEscalWild, a new benchmark dataset and training methodology for Small Language Models (SLMs) aimed at improving de-escalation skills for law enforcement. The dataset, derived from real-world…