English
Related papers

Related papers: Rethinking Generalization in Reasoning SFT: A Cond…

200 papers

Scaled post-training now drives many of the largest capability gains in language models (LMs), yet its effect on pretrained knowledge remains poorly understood. Not all forgetting is equal: Forgetting one fact (e.g., a U.S. president or an…

Machine Learning · Computer Science 2025-10-21 Jackson Harmon , Andreas Hochlehnert , Matthias Bethge , Ameya Prabhu

Large language models have emerged as powerful tools for general intelligence, showcasing advanced natural language processing capabilities that find applications across diverse domains. Despite their impressive performance, recent studies…

Computation and Language · Computer Science 2025-04-01 Elita Lobo , Chirag Agarwal , Himabindu Lakkaraju

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…

Computation and Language · Computer Science 2025-11-04 Riccardo Alberghi , Elizaveta Demyanenko , Luca Biggio , Luca Saglietti

Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…

Machine Learning · Computer Science 2026-03-31 Ali Taheri , Alireza Taban , Qizhou Wang , Shanshan Ye , Abdolreza Mirzaei , Tongliang Liu , Bo Han

Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems. However, recent studies reveal a sharp performance drop in reasoning hop generalization scenarios, where…

Computation and Language · Computer Science 2026-05-04 Zhaoyi Li , Jiatong Li , Gangwei Jiang , Linqi Song , Defu Lian , Ying Wei

Large Language Models (LLMs) with reasoning capabilities have achieved state-of-the-art performance on a wide range of tasks. Despite its empirical success, the tasks and model scales at which reasoning becomes effective, as well as its…

Computation and Language · Computer Science 2025-09-29 Nicolas Boizard , Hippolyte Gisserot-Boukhlef , Kevin El-Haddad , Céline Hudelot , Pierre Colombo

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks. Yet, growing evidence shows that these models often generate longer but ineffective chains of thought…

Machine Learning · Computer Science 2025-07-02 Jhouben Cuesta-Ramirez , Samuel Beaussant , Mehdi Mounsif

Strong reasoning capabilities can now be achieved by large-scale reinforcement learning (RL) without any supervised fine-tuning. Although post-training quantization (PTQ) and quantization-aware training (QAT) are well studied in the context…

Machine Learning · Computer Science 2025-11-20 Medha Kumar , Zifei Xu , Xin Wang , Tristan Webb

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Computation and Language · Computer Science 2024-09-10 Sonam Gupta , Yatin Nandwani , Asaf Yehudai , Mayank Mishra , Gaurav Pandey , Dinesh Raghu , Sachindra Joshi

The Superficial Alignment Hypothesis posits that almost all of a language model's abilities and knowledge are learned during pre-training, while post-training is about giving a model the right style and format. We re-examine these claims by…

Computation and Language · Computer Science 2024-10-08 Mohit Raghavendra , Vaskar Nath , Sean Hendryx

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

Computation and Language · Computer Science 2022-06-20 Michal Štefánik

Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expensive and manually annotated multi-modal data--an ultimately…

Computation and Language · Computer Science 2025-10-28 Lai Wei , Yuting Li , Chen Wang , Yue Wang , Linghe Kong , Weiran Huang , Lichao Sun

Understanding how language model capabilities transfer from pretraining to supervised fine-tuning (SFT) is fundamental to efficient model development and data curation. In this work, we investigate four core questions: RQ1. To what extent…

Machine Learning · Computer Science 2026-02-13 Simin Fan , Dimitris Paparas , Natasha Noy , Binbin Xiong , Noveen Sachdeva , Berivan Isik

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution…

Artificial Intelligence · Computer Science 2025-03-13 Kaya Stechly , Karthik Valmeekam , Subbarao Kambhampati

With the rapid advancement of Large Language Models (LLMs), the Chain-of-Thought (CoT) component has become significant for complex reasoning tasks. However, in conventional Supervised Fine-Tuning (SFT), the model could allocate…

Computation and Language · Computer Science 2025-12-25 Xiaofeng Shi , Qian Kou , Yuduo Li , Hua Zhou

Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) prompting, which enables thorough exploration and deliberation. Despite these…

Computation and Language · Computer Science 2026-04-09 Junnan Liu , Hongwei Liu , Songyang Zhang , Kai Chen

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve…

Machine Learning · Computer Science 2026-02-16 Qinhang Wu , Sen Lin , Ming Zhang , Yingbin Liang , Ness B. Shroff

Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought (Long CoT) reasoning have demonstrated remarkable cross-domain generalization capabilities. However, the underlying mechanisms supporting such transfer…

Computation and Language · Computer Science 2025-06-19 Feng He , Zijun Chen , Xinnian Liang , Tingting Ma , Yunqi Qiu , Shuangzhi Wu , Junchi Yan

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. Advances in prompt engineering and fine-tuning techniques have further enhanced their ability to address complex reasoning challenges.…

Computation and Language · Computer Science 2024-12-16 Jing Bi , Yuting Wu , Weiwei Xing , Zhenjie Wei

Reinforcement learning with verifiable reward (RLVR) has been instrumental in eliciting strong reasoning capabilities from large language models (LLMs) via long chains of thought (CoT). During RLVR training, we formalize and systemically…

Computation and Language · Computer Science 2026-02-24 Cheonbok Park , Jeonghoon Kim , Joosung Lee , Sanghwan Bae , Jaegul Choo , Kang Min Yoo
‹ Prev 1 4 5 6 7 8 10 Next ›