Paper Abstract
- ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning
- Authors: Yuwei Yin and Giuseppe Carenini
- Paper: https://huggingface.co/papers/2502.04689
Intent, a critical cognitive notion and mental state, is ubiquitous in human communication and problem-solving.
Accurately understanding the underlying intent behind questions is imperative to reasoning towards correct answers.
However, this significant concept has been largely disregarded in the rapid development of language models (LMs).
To unleash the potential of intent and instill it into LMs, this paper introduces Intentional Analysis (IA), which
explicitly invokes intent-aware analysis and reasoning during the problem-solving process. Comprehensive experiments
across diverse benchmarks, model types, and configurations demonstrate the effectiveness, robustness, and
generalizability of IA. Notably, IA consistently improves task performance even on SOTA proprietary models like
GPT-5 and Claude-Opus-4.6. Moreover, IA not only outperforms Chain-of-Thought (CoT) across various experimental
settings, but it can also synergistically work with CoT reasoning. Further qualitative analysis and case studies
reveal that the benefits of IA stem from addressing several weaknesses in baseline methods, such as intent
misunderstanding, hasty generalization, and mental laziness. Case studies also provide insights into the mechanisms
underlying IA and clarify how it differs from CoT in mitigating these weaknesses. This study sheds light on a
promising direction for the development of future LLMs with intentional analysis.
The code will be updated later.
Please refer to the LICENSE file for more details.
- Paper (arXiv): https://arxiv.org/abs/2502.04689
- If you find our work helpful, please kindly star this GitHub repo and cite our paper. 🤗
@article{yin2026ia,
title = {Improving Language Models with Intentional Analysis},
author = {Yin, Yuwei and Carenini, Giuseppe},
journal = {arXiv preprint arXiv:2502.04689},
year = {2026},
url = {https://arxiv.org/abs/2502.04689},
}