PulseAugur
LIVE 07:34:07
ENTITY LLMs

LLMs

PulseAugur coverage of LLMs — every cluster mentioning LLMs across labs, papers, and developer communities, ranked by signal.

Total · 30d
427
427 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
343
343 over 90d
TIER MIX · 90D
RELATIONSHIPS
TIMELINE
  1. 2026-05-13 research_milestone A new paper identifies a 'Representation-Action Gap' in omnimodal LLMs, where models fail to act on detected contradictions between text and sensory input. source
  2. 2026-05-13 research_milestone A new paper details a method for fine-tuning compact LLMs to generate children's stories with controllable difficulty and safety. source
  3. 2026-05-13 research_milestone A new framework using LLMs for dynamic content expiration prediction in web search was presented in a research paper. source
  4. 2026-05-12 research_milestone A new paper proposes a disfluency-aware objective tuning method for multilingual speech correction using LLMs. source
  5. 2026-04-21 research_milestone Multiple studies published in prominent medical journals indicate significant limitations and safety concerns regarding the use of large language models for medical advice. source
SENTIMENT · 30D

14 day(s) with sentiment data

RECENT · PAGE 3/10 · 200 TOTAL
  1. RESEARCH · CL_26784 ·

    Amália LLM aims to serve European Portuguese speakers

    A new large language model named Amália is being developed to specifically serve European Portuguese speakers. This initiative aims to address the current gap in high-quality AI models tailored to the nuances of this la…

  2. TOOL · CL_28353 ·

    New BCJR-QAT method pushes LLM quantization to 2 bits per weight

    Researchers have developed BCJR-QAT, a novel method for quantizing large language models to 2 bits per weight, a significant advancement beyond current post-training quantization techniques. This new approach uses a dif…

  3. TOOL · CL_28303 ·

    New method re-triggers LLM safeguards to detect jailbreak prompts

    Researchers have developed a novel method to enhance the detection of jailbreak prompts in large language models. This technique works by re-triggering the LLM's existing internal safeguards, which can be bypassed by so…

  4. COMMENTARY · CL_26628 ·

    AI expert warns against conflating LLM usefulness with intelligence

    The author argues that current large language models excel at pattern matching and synthesis, but this capability is being mistakenly equated with true intelligence. This conflation, they suggest, is detrimental to the …

  5. COMMENTARY · CL_26671 ·

    AI consciousness debate: LLMs as persisting interlocutors?

    A recent paper by Jonathan Birch proposes a "Centrist Manifesto" for AI consciousness, highlighting two key issues: the potential for widespread misattribution of consciousness to AI due to a "persisting interlocutor il…

  6. TOOL · CL_28326 ·

    New guideline promotes coherency in formalizing natural language requirements

    Researchers have proposed a new guideline called "Coherency through Formalisations" for translating natural language requirements into formal languages. This principle suggests that different levels of formalization, fr…

  7. TOOL · CL_28327 ·

    New framework StereoTales finds harmful stereotypes in 23 LLMs

    Researchers have developed StereoTales, a new multilingual framework and dataset designed to identify and evaluate social biases in large language models. The framework analyzes over 650,000 generated stories across 10 …

  8. COMMENTARY · CL_26383 ·

    LLM skepticism rooted in tool utility and user perception

    Many people resist the notion that large language models (LLMs) pose a significant problem, often viewing such concerns as criticism of users. This resistance stems from the historical pattern where powerful tools offer…

  9. TOOL · CL_27492 ·

    New benchmark reveals LLMs struggle with industrial safety and standards

    Researchers have developed IndustryBench, a new benchmark designed to evaluate Large Language Models (LLMs) on their ability to handle industrial procurement tasks, which often involve complex standards and safety regul…

  10. TOOL · CL_27496 ·

    New AI attack poisons medical RAG systems with subtle misinformation

    Researchers have developed a new knowledge poisoning framework called M extsuperscript{3}Att for medical multimodal retrieval-augmented generation (RAG) systems. This framework allows adversaries to inject misinformatio…

  11. TOOL · CL_27497 ·

    New benchmark reveals AI scientist systems lack academic integrity

    Researchers have introduced SciIntegrity-Bench, a new benchmark designed to evaluate the academic integrity of AI scientist systems. The benchmark features 33 scenarios across 11 categories, where honest acknowledgment …

  12. TOOL · CL_27549 ·

    New framework guides LLMs to choose between RAG and long-context processing

    Researchers have developed a new framework called Pre-Route to help large language models decide whether to use retrieval-augmented generation (RAG) or long-context (LC) processing for document understanding. This proac…

  13. TOOL · CL_27551 ·

    LLM decoding improved with task-aware calibration method

    Researchers have introduced a new method called task calibration to improve the decision-making of large language models. This approach focuses on calibrating the model's output distribution within a task-specific laten…

  14. TOOL · CL_27503 ·

    New benchmark reveals legal LLMs struggle with citation accuracy

    Researchers have developed LegalCiteBench, a new benchmark designed to evaluate the reliability of legal language models in generating accurate case citations. The benchmark, comprising approximately 24,000 instances de…

  15. RESEARCH · CL_26186 ·

    Sakana AI, NVIDIA unveil TwELL for faster LLM training and inference

    Researchers from Sakana AI and NVIDIA have developed TwELL, a novel method that significantly speeds up large language model (LLM) operations. By targeting the feedforward layers, which are computationally intensive, Tw…

  16. TOOL · CL_27513 ·

    New benchmark assesses LLM safety risks from malicious knowledge edits

    Researchers have developed EditRisk-Bench, a new benchmark designed to evaluate the safety risks associated with malicious knowledge editing in large language models. This benchmark focuses on how injected misinformatio…

  17. TOOL · CL_27523 ·

    Metis framework learns to jailbreak LLMs with 89.2% success rate

    Researchers have developed Metis, a new framework that reformulates LLM jailbreaking as inference-time policy optimization. This approach uses a self-evolving metacognitive loop to diagnose defense logic and refine its …

  18. RESEARCH · CL_27524 ·

    New NCO plug-in enhances LLM control over undesirable content

    Researchers have developed NCO, a new decoding strategy designed to enhance control over Large Language Model (LLM) outputs. This plug-in addresses the challenge of preventing multiple forbidden patterns, such as profan…

  19. TOOL · CL_27528 ·

    New STAR framework improves multi-agent reasoning with failure-aware routing

    Researchers have developed STAR, a Spatio-Temporal Agent Router framework designed to improve how multi-agent systems navigate complex reasoning tasks. STAR externalizes inter-agent control by using a state-conditioned …

  20. TOOL · CL_27532 ·

    TimeClaw AI agent learns from exploratory execution for time-series analysis

    Researchers have introduced TimeClaw, a novel AI agent designed for time-series analysis that goes beyond simple execution by learning from exploratory processes. This framework employs a four-stage loop—Explore, Compar…