Introduces the first community-governed unified JSON schema and crowdsourced repository for AI evaluation results, with converters and a database spanning 22,235 models and 2,273 benchmarks.
Ar-lsat: Investigating analytical reasoning of text
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
dataset 1polarities
use dataset 1representative citing papers
LLM reasoning failures split into committed (early lock-in) and persistent-uncertainty modes with distinct token-level signatures that hold across 23 model-dataset pairs in 20 of 23 falsifiable tests.
LAQuant improves long-decoding accuracy on quantized reasoning models like Qwen3-4B by 15pp on AIME25 via layer-wise lookahead loss, achieving 3.42x speedup over FP16.
SLMs achieve only a 4.4% accuracy gain from self-generated hints on reasoning benchmarks, fail to semantically distinguish useful feedback, and perform worse with longer hints.
citing papers explorer
-
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results
Introduces the first community-governed unified JSON schema and crowdsourced repository for AI evaluation results, with converters and a database spanning 22,235 models and 2,273 benchmarks.
-
How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures
LLM reasoning failures split into committed (early lock-in) and persistent-uncertainty modes with distinct token-level signatures that hold across 23 model-dataset pairs in 20 of 23 falsifiable tests.
-
LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss
LAQuant improves long-decoding accuracy on quantized reasoning models like Qwen3-4B by 15pp on AIME25 via layer-wise lookahead loss, achieving 3.42x speedup over FP16.
-
More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs
SLMs achieve only a 4.4% accuracy gain from self-generated hints on reasoning benchmarks, fail to semantically distinguish useful feedback, and perform worse with longer hints.