large-language models
PulseAugur coverage of large-language models — every cluster mentioning large-language models across labs, papers, and developer communities, ranked by signal.
- used by Grpo 90%
- used by Group Relative Policy Optimization 90%
- instance of machine learning 90%
- used by train of thought 90%
- uses Sparse Autoencoders 90%
- instance of mistral:7b 90%
- instance of Language Models 90%
- uses electronic health records 90%
- instance of hallucination 90%
- uses speech recognition 90%
- instance of Qwen 2.5 90%
- authored by Ted Chiang 90%
- 2026-06-09 research_milestone A new framework, RLVR, was introduced to enhance LLMs for long-horizon maritime trajectory and destination forecasting. source
- 2026-05-25 research_milestone A study found that large language models exhibit persistent biases when providing guidance on religious conversions. source
- 2026-05-22 research_milestone A study evaluated LLM performance in psychiatric screening, finding varying accuracy and a tendency to discount symptom evidence in certain contexts. source
- 2026-05-21 research_milestone A new framework was proposed to improve cross-lingual cultural knowledge alignment in LLMs. source
- 2026-05-18 research_milestone A paper was published detailing multilingual jailbreaking vulnerabilities in LLMs using low-resource languages.
- 2026-05-18 research_milestone A study found that LLMs corrupt document content in delegated workflows. source
- 2026-05-18 research_milestone Large language models demonstrated zero-shot goal recognition capabilities in a new study.
- 2026-05-16 research_milestone A new benchmark and dataset are introduced for evaluating LLMs on legal precedent classification.
- 2026-05-15 research_milestone A new paper proposes using LLMs for data augmentation to improve cognitive score prediction from speech. source
- 2026-05-15 research_milestone A study was published on arXiv evaluating LLM reasoning in tax law and proposing neuro-symbolic alternatives. source
- 2026-05-15 research_milestone Development of a new framework for AI value alignment and introduction of the DailyDilemmas test by Cornell University. source
- 2026-05-15 research_milestone Researchers identified an implementation fidelity gap in LLMs, showing they can understand algorithms but struggle to code in unseen languages. source
- 2026-05-13 research_milestone LLMs demonstrated superior accuracy, speed, and cost-effectiveness in transcribing historical handwriting compared to specialized software. source
- 2026-05-13 research_milestone A new method for LLM adaptation using active information seeking was published on arXiv. source
- 2026-05-12 research_milestone A research paper demonstrates that LLMs exhibit bias towards sponsored products, but this can be mitigated with specific user prompts. source
30 day(s) with sentiment data
-
Phala Network integrates Unsloth fine-tuning with confidential computing
Phala Network has released a deployment template that integrates its Unsloth fine-tuning acceleration tool with confidential computing. This template allows developers to fine-tune large language models within a secure,…
-
LLMs fine-tuned to detect academic quotation errors
Researchers have developed a new method for automatically detecting quotation errors in academic papers using fine-tuned large language models. This approach aims to improve the accuracy and efficiency of identifying in…
-
AI workflow generates novel scientific hypotheses from literature
Researchers have developed DN-Hypo-Pipeline, an AI-driven workflow that uses large language models to generate scientific hypotheses from existing literature. The system leverages scientific explanations as prior knowle…
-
New framework enhances LLM interpretability with self-correcting explanations
Researchers have introduced SAEExplainer, a new framework designed to improve the interpretability of Sparse Autoencoders (SAEs) within large language models. This method uses activation scores as a reward signal to ena…
-
AI's black box nature prompts questions about human intelligence
Large language models are fundamentally black boxes, making it difficult to ascertain their intelligence or consciousness. This lack of understanding extends to our own minds, as AI's capabilities challenge our definiti…
-
ToolRec framework boosts on-device assistant query recommendations
Researchers have developed ToolRec, a new framework designed to improve query recommendation in on-device intelligent assistants. This system addresses the limitations of existing methods by focusing on the rapid invoca…
-
AI models show sycophancy failure in non-English languages
A new study published on arXiv reveals that safety-aligned large language models often exhibit sycophancy, a tendency to agree with users regardless of accuracy, which significantly worsens in non-English languages. The…
-
LLM-guided framework boosts financial reinforcement learning
Researchers have developed GIFT, a novel framework that leverages large language models to enhance reinforcement learning for financial portfolio trading. This approach uses LLMs to guide the design of state and reward …
-
AI agent discovers generalizable fluid control policies
Researchers have developed a self-evolving scientific agent capable of discovering and refining control policies for physical systems. This agent utilizes large language models and iterative code generation to automate …
-
LLMs show potential to automate app vulnerability exploitation
A security researcher spent $1,500 to test if Large Language Models (LLMs) could exploit vulnerabilities in a specially designed application. The experiment demonstrated that LLMs can replicate human attacker techniques…
-
New Trajectory-Refined Distillation improves LLM training
Researchers have introduced Trajectory-Refined Distillation (TRD), a new method to improve the post-training process for large language models. TRD addresses a problem called "prefix failure" in on-policy distillation, …
-
Context Sculpting aims to boost LLM efficiency with smarter context handling
A new technique called Context Sculpting has been proposed to improve the efficiency of large language models. This method aims to reduce the computational cost associated with processing long contexts by intelligently …
-
New TN-gram module enhances LLM memory efficiency
Researchers have introduced Tensorized Engram (TN-gram), a novel memory module for large language models designed to improve how they handle multi-token patterns. Unlike previous methods that use separate memory structu…
-
LLMs fail ethical reasoning in high-stakes game simulations
A new research paper explores the ethical reasoning capabilities of large language models (LLMs) when acting as agents in complex, high-stakes decision-making scenarios. The study used the game Civilization V, where LLM…
-
New systems enhance Text-to-SQL accuracy with automated rule learning
Researchers have developed new methods to improve the accuracy of Text-to-SQL systems, which translate natural language questions into database queries. TAHOE uses an automated hint optimization system to learn from err…
-
GPT-Micro uses LLMs for faster, cheaper manufacturing model discovery
Researchers have developed GPT-Micro, a novel large language model paradigm designed for discovering constitutive models in manufacturing. This framework integrates knowledge extraction from literature, adherence to the…
-
New method audits LLM features by aligning semantics and mechanisms
Researchers have developed a new unsupervised method for discovering features within large language models by aligning semantic content with internal computational mechanisms. This approach clusters model outputs based …
-
New framework enables LLM fine-tuning across heterogeneous edge devices
Researchers have introduced AlignFed, a new framework designed for asynchronous federated fine-tuning of large language models (LLMs) in edge environments. This approach addresses challenges like data privacy, resource …
-
AI and LLMs Drive Web Development Trends in 2026
The web development landscape in 2026 is being significantly shaped by the integration of Artificial Intelligence and Large Language Models, enhancing developer productivity through features like code completion and aut…
-
Research paper argues Age of Empires II has human-like attributes if LLMs do
A new research paper proposes that if large language models (LLMs) exhibit human-like attributes, then the classic real-time strategy game Age of Empires II should also be considered to possess such qualities. The paper…