1
Why your LLM ignores what you asked for
揭秘大模型为何“答非所问”，从提示工程到上下文机制，帮你避开常见误区，提升指令精准度。
Article URL: https://github.com/CamjamPNG/skills Comments URL: https://news.ycombinator.com/item?id=49280922 Points: 3 # Comments: 0
2
UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following
破解大模型指令遵循中的复制粘贴捷径，用通用约束合成让模型真正理解复杂指令，AI训练方法论新突破
arXiv:2608.09154v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly expected to follow long lists of constraints in complex …
3
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
多约束指令总翻车？DeCRIM用分解-批判-修正三步，让LLM自我纠错能力显著提升。
arXiv:2410.06458v2 Announce Type: replace-cross Abstract: Instruction following is a key capability for LLMs. However, recent studies have shown that …
4
Can Large Language Models Execute Parent Orders?
用大模型拆分并执行机构级父订单，实测其在交易调度与指令执行上的边界，金融自动化新看点。
arXiv:2607.28410v1 Announce Type: cross Abstract: Parent-order execution is a core problem in algorithmic trading, where the goal is to split a large …
5
True open-source LLM Apertus 1.5 released
开源大模型Apertus 1.5登场，8B/70B双版本加持262k超长上下文，指令遵循能力再升级。
Article URL: https://www.apertus-ai.org/articles/2026-07-apertus-1-5/ Comments URL: https://news.ycombinator.com/item?id=49050483 Points: 3 # Comments…
6
LogicIF: Towards Complex Logic Instruction Following
大模型逻辑指令遵循新方法LogicIF被COLM 2026接收，挑战复杂逻辑推理场景
arXiv:2508.09125v3 Announce Type: replace-cross Abstract: Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is th…
7
Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse
当指令出错时，代码大模型会如何反应？这项研究揭示盲从导致不可逆的语义崩溃。
arXiv:2607.04537v1 Announce Type: cross Abstract: Code language models are now trusted collaborators in production workflows for debugging, refactorin…
8
WildIFEval: Instruction Following in the Wild
新基准WildIFEval带你从实验室走进真实世界的指令跟随能力评估
arXiv:2503.06573v3 Announce Type: replace-cross Abstract: Recent LLMs have shown remarkable success in following user instructions, yet handling instr…
9
LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
全新方法LsrIF，让大模型更精准理解逻辑结构化指令，推理能力显著提升！
arXiv:2601.06431v3 Announce Type: replace Abstract: Instruction following is critical for large language models, yet real-world instructions often inv…