paper-with-me

Papers

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities

2025-03-23 · Weixiang Zhao, Xingyu Sui, Jiahe Guo, Yulin Hu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Tat-Seng Chua, Ting Liu

Recent advancements in Large Reasoning Models (LRMs), such as OpenAI's o1/o3 and DeepSeek-R1, have demonstrated remarkable performance in specialized reasoning tasks through human-like deliberative thinking and long chain-of-thought reasoning. However, our systematic evaluation across various model families (DeepSeek, Qwen, and LLaMA) and scales (7B to 671B) reveals that acquiring these deliberative reasoning capabilities significantly reduces the foundational capabilities of LRMs, including notable declines in helpfulness and harmlessness, alongside substantially increased inference costs. Importantly, we demonstrate that adaptive reasoning -- employing modes like Zero-Thinking, Less-Thinking, and Summary-Thinking -- can effectively alleviate these drawbacks. Our empirical insights underline the critical need for developing more versatile LRMs capable of dynamically allocating inference-time compute according to specific task characteristics.

📄 PDF Abstract BibTeX arXiv:2503.17979

Code (1)

SCIR-SC-Qiaoban-Team/FreeEvalLM 공식 구현

Similar Papers 제목 키워드 기반

Benefits and Limitations of Communication in Multi-Agent Reasoning

2025-10-14 · Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi, Guillaume Rabusseau 외 arxiv

Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long con…

Federated Unlearning: a Perspective of Stability and Fairness

2024-02-02 · Jiaqi Shao, Tao Lin, Xuanyu Cao, Bing Luo

This paper explores the multifaceted consequences of federated unlearning (FU) with data heterogeneity. We introduce key metrics for FU assessment, concentrating on verification, global stability, and local fairness, and…

Fairness

ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

2026-06-05 · Vladislav Smirnov, Chieu Nguyen, Sergey Senichev, Minh Ngoc Ta 외 arxiv

Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via multi-sample generation and verifier-base…

Computational Efficiency

Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL

2025-12-26 · Saurabh Deochake, Debajyoti Mukhopadhyay arxiv

While Text-to-SQL systems achieve high accuracy, existing efficiency metrics like the Valid Efficiency Score prioritize execution time, a metric we show is fundamentally decoupled from consumption-based cloud billing. Th…

Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency Tradeoffs

2026-01-10 · Deep Mehta arxiv

Self-consistency has emerged as a popular technique for improving large language model accuracy on reasoning tasks. The approach is straightforward: generate multiple reasoning paths and select the most common answer thr…

Mathematical Reasoning