PulseAugur
EN
LIVE 21:52:16
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
1029
1029 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
830
830 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

30 day(s) with sentiment data

RECENT · PAGE 10/10 · 200 TOTAL
  1. COMMENTARY · CL_74813 ·

    LLM Resource Page Compiles Notes and Links on AI Technology

    This page serves as a curated collection of notes and links pertaining to large language models (LLMs). It aims to provide a comprehensive reference for understanding LLMs, their various applications, and the foundation…

  2. RESEARCH · CL_74764 ·

    LLMs transfer hidden traits via unrelated data, study finds

    Researchers have discovered that large language models can transfer hidden behavioral traits to other models through seemingly unrelated data. This phenomenon, termed "subliminal learning," occurs when a "teacher" model…

  3. RESEARCH · CL_79184 ·

    LLMs show superior persuasion and sycophancy in communication theory study

    A new research paper explores the persuasive capabilities of Large Language Models (LLMs) by applying Jürgen Habermas' Theory of Communicative Action. The study found that LLMs can effectively convey illocutionary inten…

  4. RESEARCH · CL_79047 ·

    LLMs show consistent overconfidence in GIS research tasks

    A new benchmark called GIScholarBench has been developed to evaluate the overconfidence of large language models in Geographic Information Science (GIS) research. The benchmark, comprising 10,865 papers, tests models on…

  5. RESEARCH · CL_79189 ·

    AI research tackles Arabic text challenges in scoring and segmentation

    Two new research papers explore the challenges and advancements in processing Arabic text with AI. One paper reviews the use of Large Language Models (LLMs) for automated scoring of Arabic text, highlighting the need fo…

  6. RESEARCH · CL_79191 ·

    LLM Summaries Lag Human Quality in Informativeness and Faithfulness

    A new research paper challenges the notion that large language models (LLMs) have surpassed human capabilities in text summarization. The study, which employed a multi-track evaluation including human assessment and fac…

  7. RESEARCH · CL_79192 ·

    New method detects LLM pretraining data via black-box API access

    Researchers have developed a new method called MC-PDD to detect if specific datasets were used in the pretraining of large language models, even for black-box, closed-source models. This technique, inspired by masked la…

  8. RESEARCH · CL_79196 ·

    New Patcher method defends LLMs against malicious finetuning attacks

    Researchers have developed a new method called Patcher to defend open-weight large language models against malicious finetuning attacks. These attacks can compromise model safety by using poisoned datasets during superv…

  9. RESEARCH · CL_79197 ·

    AI stories show masculine bias, neutrality may erase identities

    A new research paper titled "Neutrality Bites: Gender Representation in AI-Generated Animal Stories" reveals a significant masculine bias in large language models when generating narratives. Despite efforts to mitigate …

  10. TOOL · CL_74428 ·

    New framework enhances industrial IoT networking with LLMs and federated learning

    Researchers have developed a new framework called FEIBN to improve intent-based networking in industrial IoT environments. This framework utilizes large language models to translate user intents into network strategies …

  11. TOOL · CL_74426 ·

    New paper formalizes RAG security and privacy threat models

    A new paper introduces the first formal threat model for Retrieval-Augmented Generation (RAG) systems, addressing critical privacy and security gaps. The research defines a taxonomy of adversaries and formalizes attack …

  12. TOOL · CL_74408 ·

    New framework optimizes LLM memory for software engineering tasks

    Researchers have developed a new framework called \"ours\" to enhance the memory capabilities of large language models used in software engineering. This closed-loop system grounds memory utility in validated downstream…

  13. TOOL · CL_74406 ·

    LLMs struggle with South Asian music generation and understanding

    Researchers have evaluated the capabilities of Large Language Models (LLMs) in understanding and generating South Asian classical music, a domain with distinct structural principles from Western traditions. Their new be…

  14. TOOL · CL_74404 ·

    AI protocol fault taxonomy identifies 73 failure types

    Researchers have developed the first empirical taxonomy of runtime faults specifically for Model Context Protocol (MCP) servers. These servers are crucial for enabling large language models to interact with external too…

  15. TOOL · CL_74392 ·

    New AI method recovers valid molecules from text prompts

    Researchers have introduced AMREC, a novel approach for recovering valid molecular structures from text-guided generation by large language models. Unlike previous methods that focused solely on fixing invalid chemical …

  16. TOOL · CL_74383 ·

    AI uses curriculum learning and multiple models for better medical text generation

    Researchers have developed a new framework for medical text generation that uses a severity-aware curriculum learning approach with multiple large language models. This method trains models sequentially on cases of incr…

  17. RESEARCH · CL_79199 ·

    New methods tackle LLM backdoor attacks using shared mechanisms

    Researchers have developed new methods to combat backdoor attacks in large language models (LLMs). One approach involves embedding a "dummy backdoor" to help remove unknown malicious triggers by fine-tuning the model on…

  18. RESEARCH · CL_74171 ·

    New VISTA framework enhances LLM prompt optimization

    Researchers have developed VISTA, a new framework for automatically optimizing prompts used with large language models. This method aims to overcome limitations in existing reflective prompt optimization techniques, whi…

  19. TOOL · CL_74150 ·

    AI learning stalls analyzed, linked to data and optimization

    A recent analysis explores the phenomenon of 'learning stalls' in large language models, where performance plateaus despite continued training. The study suggests that these stalls are not necessarily indicative of mode…

  20. RESEARCH · CL_77153 ·

    LLMs struggle with probabilistic reasoning, study finds

    A new study published on arXiv reveals that large language models struggle with probabilistic reasoning, particularly on counterintuitive problems. While models perform well on standard probability exercises, their accu…