Web This site Trusted
30 result(s) for “okapi bm25 site terms com pp site github com site lemmy world site going in site:arxiv.org” of 37 matched · 741 ms
Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.
Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)
The query asks the model to recall the topic of an earlier conversation about Tesla; the gold answer is anchored in one specific session about Pooja’s dig site
from the top result below
https://arxiv.org/html/2608.02613v1
1 Introduction
As the world accelerates its adoption of agentic AI, it becomes crucial to build and assess the agents’ capability and capacity in retaining information
https://arxiv.org/html/2608.03048v1
com/JetAstra/PI-Mem
Introduction
The ability to reason over long contexts is increasingly important for large language models (LLMs), supporting applications such as long-document question answering (Gemini Team 2025; Yang et al
https://arxiv.org/html/2501.13956v1
com
Abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark
https://arxiv.org/html/2407.16741v3
edu
Abstract
Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways
https://arxiv.org/html/2608.02668v1
com/hazdzz/deep_connection \ncudata[Correspondence]Jie Zhang (),
Correspondence: Cheng-Fang Su ()
“Geometry is not true, it is advantageous
https://arxiv.org/html/2608.03011v1
In practice, however, audio prompts are often recorded under diverse real-world acoustic conditions, where various environmental factors such as background noise and room reverberation are inevitably present
https://arxiv.org/html/2608.03063v1
8 pp in a production fraud detector serving billion-scale transaction traffic
https://arxiv.org/list/cs.AI/new
In practice, many field descriptions remain ambiguous or incomplete, as much of the essential context (e
https://arxiv.org/html/2608.02918v1
Miranda is also with LCTI, Télécom Paris, IP Paris, France
https://arxiv.org/html/2607.22511v2
We present CausalForge, a framework for automated theoretical research in causal inference grounded in the Lean proof assistant
https://arxiv.org/html/2608.02609v1
edu
Abstract
Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world’s oldest writing system, leaving a 4,000-year cultural barrier that existing NLP tools have only partially addressed
https://arxiv.org/html/2407.17789v2
com/modelscope/agentscope/tree/main/examples/paper_large_scale_simulation to inspire further research and development in large-scale multi-agent simulations
https://arxiv.org/list/cs.CL/new
LG)
Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world's oldest writing system, leaving a 4,000-year cultural barrier that existing NLP tools have only partially addressed
https://arxiv.org/html/2407.02518v2
com
Abstract
Large language models (LLMs) for code are typically trained to align with natural language instructions to closely follow their intentions and requirements
https://arxiv.org/html/2210.00131v4
Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution
1 Introduction
1
https://arxiv.org/html/2509.22186v2
com/opendatalab/MinerU \metadata[Model:]https://huggingface
https://arxiv.org/html/2608.02612v1
In contrast, many important real-world tasks, including hyperparameter optimization, molecular design, and structural shape optimization, are more naturally cast as black-box optimization (BBO) problems
https://arxiv.org/html/2508.16279v1
In line with such an evolution, AgentScope introduces major improvements in a new version (1
https://arxiv.org/html/2508.19205v1
com/microsoft/VibeVoice
Hugging Face: microsoft/VibeVoice
Demo: aka
https://arxiv.org/html/2608.03446v1
com/KathyHaem/cla-metrics
2 Background and Related Work
Cross-lingual alignment
https://arxiv.org/html/2608.02616v1
com
Abstract
We present the first independent, systematic evaluation of OpenAI’s Privacy Filter (OPF), a 1
https://arxiv.org/html/2608.00785v1
com
Abstract
Content discovery systems depend on relevance judgment for search quality evaluation, but human annotation faces inter-annotator disagreement and scaling costs
https://arxiv.org/html/2402.03300v3
com/deepseek-ai/DeepSeek-Math
Abstract
Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature
https://arxiv.org/html/2506.01844v1
While complementary in terms of modalities, such advances in developing multi-modal foundation models stem from (i) the adoption of scalable architectures, such as the Transformer (Vaswani, 2017) and (ii) internet-scale training datasets
https://arxiv.org/html/2403.08299v1
2 Evaluation of LLMs in Software Engineering
6
https://arxiv.org/html/2608.03486v1
Identification is achieved by exploiting variation in the conditional distributions of the mutually independent structural shocks induced by an observed exogenous variable
https://arxiv.org/list/cs.SE/new
Through an analysis of 1,966 open source projects, 1,355 Github issues, 444 CVE reports, and 361 StackOverflow posts, we systematically map the feature support and real-world usage of globs across six common ecosystems that utilize globs
https://arxiv.org/abs/2608.03883
All submitted systems follow a staged retrieval design in which BM25 retrieves candidates at scale and semantic or LLM rerankers refine the final rankings
https://arxiv.org/abs/2104.08663
Benchmark for Zero-shot Evaluation of Information Retrieval Models, by Nandan Thakur and 4 other authors
View PDF HTML (experimental)
Abstract:Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of
https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation