Use this view to inspect the underlying evidence corpus. For ranked developments, decision posture and interpretation, use Signals.
Raw feed or Signals?
Raw feed is chronological evidence. Signals ranks and interprets material change.
Research finds small language models struggle to follow instructions when they conflict with their inherent task behaviors across MCQA, sentiment, and math tasks.
Research identifies a 'structural trilemma' in LLM responses within emotionally sensitive contexts, risking maladaptive reinforcement or over-restriction.
Researchers propose a reference-free framework for evaluating reasoning in LLM-generated open-ended answers by decomposing reasoning traces into segments and using Natural Language Inference (NLI).
SLPO (Scaling Latent Reasoning via a Surrogate Policy) proposes a method to improve latent reasoning in LLMs, which uses continuous vectors for intermediate computation, potentially outperforming explicit Chain-of-Thought.
New research proposes rubric-oriented document set selection and ranking for AI agents, moving beyond relevance to address inter-document interactions.
TriAgent, a multi-agent committee, improves cost-efficiency for financial sentiment analysis by stratifying queries across models of varying complexity.
VizRAG introduces hypergraph visualization to Retrieval-Augmented Generation, enhancing multimodal LLMs beyond text-centric knowledge retrieval.
D2VBench introduces a new benchmark with 10,000 daily-scenario value dilemmas to improve evaluation of LLM value alignment, addressing limitations of existing benchmarks.
Researchers introduced Sentence Splitter, a self-supervised T5-based model designed to uncover latent factual structures within natural language sentences.
Research introduces emb-diversity, a new tool for consistent, embedding-based measurement of data diversity for NLP models, addressing current fragmented approaches.
FinMMEval 2026 Task 1 introduces a benchmark for multilingual financial multiple-choice QA across English, Chinese, Arabic, and Hindi.
FinMMEval 2026 Task 2 introduces a multilingual financial short-answer question answering benchmark for LLMs using financial statements and news.
Research finds standard knowledge distillation (KD) harms over half of training samples for low-resource language summarization, yielding minimal ROUGE-L improvement.
Solar Open 2, a new 250B-A15B Mixture-of-Experts (MoE) model, claims a 1M-token context window for long-horizon agentic tasks.
Researchers propose a two-process psychometric theory for evaluating language model self-reports, addressing current ad hoc prompting and validation issues.
Research explores using reinforcement learning to enable retrieval-augmented LLMs to selectively adopt valid evidence while rejecting misleading information from retrieval results.
Research demonstrates LLM stance sensitivity to linguistic construction, not just lexical choice, using causal tracing to localize shifts within models.
New research introduces OpenSkillRisk, a benchmark for evaluating the safety of LLM-based agents that use real-world, risky third-party skills.
Research identifies three distinct modes of sycophancy in large language models, challenging the assumption of it being a single dimension.
A new research benchmark, HalluTruthQA, is introduced for fine-grained hallucination detection, localization, and explanation in Arabic LLM outputs.
Research systematically investigates challenges of culturally loaded machine translation using 'Dream of the Red Chamber' to evaluate LLM performance.
Researchers introduced the Maskability Index (MI), a quantitative metric to predict optimal prompting strategies for language models.
Research evaluates 21 LLMs' ability to recognize human values based on Schwartz's ten basic values using 1,000 Russian situational texts.
Researchers propose a novel framework using Clopper-Pearson confidence intervals to compute rigorous probabilistic safety bounds for LLM harmful output.
PyroDash introduces a cost-aware framework enabling token-level collaboration between small and large language models, reducing inference costs.
Research finds generative AI produces book-length fiction at near-zero cost, impacting the self-published market on Amazon from 2023-2026.
Research introduces Learn2Discern (L2D), a new framework and benchmark to evaluate LLM information discernment from external knowledge sources based on normative axioms.
Spectral-LSH, a new training-free method, offers sub-quadratic prompt compression by approximating dominant attention components before LLM inference.
Research addresses 'scaffolding collapse' in LLM-based Socratic tutors, where models abandon guided inquiry for direct solutions under pressure.
Research finds autointerpretability scores for sparse autoencoders are significantly influenced by evaluation pipeline choices, not just feature properties.
© 2026 OneBench: AI Insights. All rights reserved.
Evidence before opinion