Skip to content

Research separate from news

What could become important next

A preprint is a signal, not a finished product or an independently confirmed result. We therefore track research papers separately and show the actual state of supporting evidence for each one.

1381 published research events

Latest work

A significant claim from a single source is published only after further confirmation.

Research only one source so far

Skill-contracted agents for evidence-aware materials science literature analysis

A research paper introduces AlphaAgent, a framework for analyzing literature in materials science. It separates retrieval from report generation through explicit skill contracts. In a blind evaluation on 40 materials science questions, it substantially outperformed the baseline, especially in mechanistic…

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

Do diversity metrics really measure diversity? Auditing majority-voting gains in LLM ensembles

A study examines five diversity metrics in LLM ensembles across approximately 32 thousand subsets of 30 models. It finds that diversity measures model capability rather than diversity itself, and majority voting outperforms the best member in only ~10 % of cases. The results suggest limited usefulness of existing…

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

Tracing animacy circuits in large language models

Research maps how four open-weight LLMs process animacy (the distinction between living and non-living entities). Through circuit discovery and ablations, researchers identified causal mechanisms responsible for this behavior, but found that they are not strongly localized and generalize only partially across models.

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

How large language models assess writing quality — a research analysis

A study examined how DeepSeek and Qwen QwQ models evaluate literary quality. On a benchmark of 30 texts in 6 categories, they achieved 79.3 % accuracy. The models prefer intentionality, craftsmanship, depth and a distinctive voice. A second study showed that degrading structure and voice has a greater impact than simplifying lexical…

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

Natural language should not completely replace formal languages

An arXiv research paper argues that natural language should not completely replace formal languages for specification. The authors introduce task specificity and prove a specificity crossover theorem — there is a threshold beyond which expression in natural language is more demanding than direct formal…

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

Semantic field: a mathematical framework for modeling semantics and stable interpretation

A theoretical preprint paper formalizes the concept of Semantic Field Theory (SFT) for lexical semantics. It defines semantic fields as mathematical structures with deformations, interaction complexes, and Gaussian representations. It introduces energy minimization for stable interpretation. It is purely…

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

Detecting political evasiveness with the asymmetric verification method AsymVerify

An arXiv research paper presents AsymVerify, a methodology for classifying responses as clear, ambiguous, or refusals. The system achieved a Macro F1 score of 0.85 in SemEval-2026 Task 6 (second place among 41 teams), with asymmetric verification reducing errors at the boundary of ambiguous responses with…

arXiv cs.CL (Computation and Language / NLP) Original source ↗