Skip to content
Tagged articles

Open-Ended Generation

2 articles · Page 1 of 1
PaperAgent
PaperAgent
Oct 15, 2026 · Artificial Intelligence

Thinking Inertia: LLMs Keep Reasoning Even When Told Not To, Tsinghua Study Shows

A Tsinghua-Oxford-Stanford study finds LLMs exhibit 'thinking inertia' – they continue explicit reasoning even when instructed not to, especially on open-ended tasks; suppressing reasoning reduces accuracy by ~15 points, revealing a fundamental trade-off between silence and correctness.

AI researchAnswer FormatLLM reasoning
0 likes · 10 min read
Thinking Inertia: LLMs Keep Reasoning Even When Told Not To, Tsinghua Study Shows
Machine Heart
Machine Heart
Sep 30, 2026 · Artificial Intelligence

ME-Decoding: Reframing LLM Decoding as Ensemble Pruning with Semantic Redundancy Control

Renmin University researchers propose ME-Decoding, a method that selects candidate tokens by jointly optimizing probability confidence and semantic diversity via Mahalanobis distance, outperforming probability-only truncation on reasoning and open-ended generation across multiple models and temperatures with only 3% latency overhead.

EMNLP 2026LLM decodingMahalanobis distance
0 likes · 11 min read
ME-Decoding: Reframing LLM Decoding as Ensemble Pruning with Semantic Redundancy Control