A Survey of LLM Alignment: Instruction Understanding, Intention Reasoning, and Reliable Generation
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Large language models have demonstrated exceptional capabilities in understanding and generation. However, in real-world scenarios, users' natural language expressions are often inherently fuzzy, ambiguous, and uncertain, leading to challenges such as vagueness, polysemy, and contextual ambiguity. This paper focuses on three challenges in LLM-based text generation tasks: instruction understanding, intention reasoning, and reliable dialog generation. Regarding human complex instruction, LLMs have deficiencies in understanding long contexts and instructions in multi-round conversations. For intention reasoning, LLMs may have inconsistent command reasoning, difficulty reasoning about commands containing incorrect information, difficulty understanding user ambiguous language commands, and a weak understanding of user intention in commands. Besides, In terms of Reliable Dialog Generation, LLMs may have unstable generated content and unethical generation. To this end, we classify and analyze the performance of LLMs in challenging scenarios and conduct a comprehensive evaluation of existing solutions. Furthermore, we introduce benchmarks and categorize them based on the aforementioned three core challenges. Finally, we explore potential directions for future research to enhance the reliability and adaptability of LLMs in real-world applications.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 12 of its 117 references that are in the map. First posted on arXiv 13 Feb 2025.
Builds on
12 of 117 references.
References · 12
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
- 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
- 2022Mass-Editing Memory in a Transformercited by 976
- 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
- 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
- 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
- 2023Orca: Progressive Learning from Complex Explanation Traces of GPT-4cited by 369
- 2023LongLoRA: Efficient Fine-tuning of Long-Context Large Language Modelscited by 243
- 2024LongAlign: A Recipe for Long Context Alignment of Large Language Modelscited by 102
- 2023Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Settingcited by 20
- 2024LOGO -- Long cOntext aliGnment via efficient preference Optimizationcited by 9
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2025The Instruction Gap: LLMs get lost in Following Instruction
- 2024Easy Problems That LLMs Get Wrong
- 2026Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions
- 2024Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
- 2024LLM With Tools: A Survey
- 2023TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs
- 2025Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
- 2025Position: On the Methodological Pitfalls of Evaluating Base LLMs for Reasoning