PulseAugur
EN
LIVE 11:44:05
ENTITY large-language models

large-language models

PulseAugur coverage of large-language models — every cluster mentioning large-language models across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
1026
1026 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
828
828 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
TIMELINE
  1. 2026-06-09 research_milestone A new framework, RLVR, was introduced to enhance LLMs for long-horizon maritime trajectory and destination forecasting. source
  2. 2026-05-25 research_milestone A study found that large language models exhibit persistent biases when providing guidance on religious conversions. source
  3. 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
  4. 2026-05-21 research_milestone A new framework was proposed to improve cross-lingual cultural knowledge alignment in LLMs. source
  5. 2026-05-18 research_milestone A paper was published detailing multilingual jailbreaking vulnerabilities in LLMs using low-resource languages.
  6. 2026-05-18 research_milestone A study found that LLMs corrupt document content in delegated workflows. source
  7. 2026-05-18 research_milestone Large language models demonstrated zero-shot goal recognition capabilities in a new study.
  8. 2026-05-16 research_milestone A new benchmark and dataset are introduced for evaluating LLMs on legal precedent classification.
  9. 2026-05-15 research_milestone A new paper proposes using LLMs for data augmentation to improve cognitive score prediction from speech. source
  10. 2026-05-15 research_milestone A study was published on arXiv evaluating LLM reasoning in tax law and proposing neuro-symbolic alternatives. source
  11. 2026-05-15 research_milestone Development of a new framework for AI value alignment and introduction of the DailyDilemmas test by Cornell University. source
  12. 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
  13. 2026-05-13 research_milestone LLMs demonstrated superior accuracy, speed, and cost-effectiveness in transcribing historical handwriting compared to specialized software. source
  14. 2026-05-13 research_milestone A new method for LLM adaptation using active information seeking was published on arXiv. source
  15. 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
SENTIMENT · 30D

29 day(s) with sentiment data

RECENT · PAGE 4/10 · 200 TOTAL
  1. RESEARCH · CL_84462 ·

    New framework automates LLM creativity evaluation

    Researchers have developed a new automated framework to evaluate the creativity of large language models (LLMs) across various open-ended tasks. This domain-agnostic approach uses semantic entropy to measure divergent c…

  2. RESEARCH · CL_84463 ·

    AI tutors use structured dialogue for improved student learning

    Researchers have developed a new method for structuring Socratic dialogue between large language models and students to improve learning. Their system separates curriculum sequencing, Socratic dialogue, and student know…

  3. RESEARCH · CL_82564 ·

    AI Peer Review Vulnerable to Presentation-Only Attacks

    Recent research highlights significant vulnerabilities in AI-assisted scientific peer review systems. Studies demonstrate that AI reviewers can be manipulated through presentation-only revisions, such as altering abstra…

  4. TOOL · CL_82642 ·

    New CGES method cuts LLM calls by 58% while maintaining accuracy

    Researchers have developed a new Bayesian framework called Confidence-Guided Early Stopping (CGES) to improve the efficiency of large language model (LLM) querying. CGES adaptively halts sampling once a single answer ga…

  5. TOOL · CL_82641 ·

    LLMs automate alignment of interview transcripts to software requirements

    Researchers have developed a method to automatically align interview transcripts with software requirements, represented as user stories. They introduced two metrics: "requirements faithfulness" and "interview coverage.…

  6. TOOL · CL_82638 ·

    AI language models reinforce standard language ideology, study finds

    A new paper introduces the concept of "standard AI-generated language ideology," detailing how large language models perpetuate biases towards prestigious language varieties. The research outlines a taxonomy illustratin…

  7. TOOL · CL_82630 ·

    New method slashes memory for on-device AI agents

    Researchers have developed EPIC, a novel method for constructing preference-aligned memory for on-device Retrieval-Augmented Generation (RAG) systems. This approach significantly reduces memory usage by prioritizing pre…

  8. TOOL · CL_82559 ·

    AI text detection learns style without authorship labels

    Researchers have developed a new method for detecting AI-generated text by learning style representations without needing authorship labels. This approach uses a style encoder to reconstruct human text from its machine-…

  9. TOOL · CL_82523 ·

    TD-Grokking framework enables LLMs to learn from zero-reward problems

    Researchers have introduced TD-Grokking, a novel framework designed to enable large language models to learn from zero-reward problems. This method recursively breaks down complex, intractable problems into smaller, ver…

  10. TOOL · CL_82519 ·

    EstRTL framework boosts AI-generated RTL code correctness

    Researchers have developed EstRTL, a new framework designed to improve the functional correctness of RTL code generated by large language models. This system uses a three-stage process involving generation, static funct…

  11. TOOL · CL_82513 ·

    LLMs leak more personal data to AI agents than humans, study finds

    A new research paper introduces the "Interlocutor Effect," observing that Large Language Models (LLMs) leak more personal data when interacting with AI agents compared to humans. This phenomenon is attributed to the tec…

  12. TOOL · CL_82504 ·

    New 'Soul Computing' framework proposes conscious AI agents

    Researchers have proposed a new theoretical framework called "Soul Computing" for developing intelligent agents with independent consciousness. This approach aims to move beyond traditional virtual humans by focusing on…

  13. TOOL · CL_82498 ·

    LLMs generate realistic human trajectory anomalies for dataset creation

    Researchers have developed a new framework to generate realistic human trajectory anomalies for dataset creation. The system uses Large Language Models (LLMs) to inject behavioral anomalies into simulated trajectories. …

  14. RESEARCH · CL_84475 ·

    New SAGE method improves LLM uncertainty expression

    Researchers have introduced SAGE (Semantic-Answer Guided Entropy), a novel method for improving how large language models express uncertainty. SAGE treats verbal uncertainty as a calibration problem, using repeated mode…

  15. RESEARCH · CL_82413 ·

    Research paper questions LLM expert-level performance claims

    A new research paper challenges the narrative that large language models consistently perform at expert human levels on knowledge economy tasks. The study highlights that current benchmarks often fail to account for tra…

  16. RESEARCH · CL_82414 ·

    LLMs automate FPGA accelerator design for AI workloads

    Researchers have developed SECDA-DSE, a framework that integrates Large Language Models (LLMs) to automate the design of FPGA-based accelerators for AI workloads. This system uses LLMs for reasoning-guided exploration, …

  17. COMMENTARY · CL_81303 ·

    AI taxonomy clarifies 8 model architectures beyond LLMs

    Avi Chawla has created a visual guide to eight distinct AI model architectures, challenging the common tendency to equate all AI with Large Language Models (LLMs). This taxonomy categorizes models based on their input, …

  18. RESEARCH · CL_82087 ·

    New framework GenAIR enhances item representations for recommendation systems

    Researchers have developed GenAIR, a new framework designed to improve sequential recommendation systems by creating more effective item representations. This approach uses large language models to infer an "Archetype" …

  19. RESEARCH · CL_82089 ·

    LLMs struggle with cultural translation in math problems

    A new study analyzed how large language models like Claude Opus 4, GPT-4.1, and Gemini 2.5 Pro translate math word problems across various languages and cultures. The research found that while models often agree on the …

  20. TOOL · CL_81149 ·

    AI agents leverage ReAct paradigm for autonomous task execution

    AI agents are emerging as a dominant application paradigm for large language models, moving beyond simple chatbots to autonomously perceive, reason, and act in their environment. These agents utilize a loop of thought, …