English
Related papers

Related papers: G-Zero: Self-Play for Open-Ended Generation from Z…

200 papers

To complete an open-ended programming exercise, students need to both plan a high-level solution and implement it using the appropriate syntax. However, these problems are often autograded on the correctness of the final submission through…

Computation and Language · Computer Science 2025-04-15 Mehmet Arif Demirtaş , Claire Zheng , Max Fowler , Kathryn Cunningham

Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectively self-verify and generate correct feedback, further…

Computation and Language · Computer Science 2025-05-28 Xiaoshuai Song , Yanan Wu , Weixun Wang , Jiaheng Liu , Wenbo Su , Bo Zheng

On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision. Existing methods usually assume trusted PI, such as reference…

Computation and Language · Computer Science 2026-05-28 Jiazhen Huang , Xiao Chen , Xiao Luo , Yong Dai , Senkang Hu , Yuzhi Zhao

We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward models from human preferences, which may then be bottlenecked by…

Computation and Language · Computer Science 2025-03-31 Weizhe Yuan , Richard Yuanzhe Pang , Kyunghyun Cho , Xian Li , Sainbayar Sukhbaatar , Jing Xu , Jason Weston

Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…

Computation and Language · Computer Science 2022-10-25 Jiacheng Ye , Jiahui Gao , Jiangtao Feng , Zhiyong Wu , Tao Yu , Lingpeng Kong

Recent advances in test-time scaling have led to the emergence of thinking LLMs that exhibit self-reflective behaviors and multi-step reasoning. While RL drives this self-improvement paradigm, a recent study (Gandhi et al., 2025) shows that…

Artificial Intelligence · Computer Science 2025-08-22 Aswin RRV , Jacob Dineen , Divij Handa , Md Nayem Uddin , Mihir Parmar , Chitta Baral , Ben Zhou

Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in recognizing novel classes in the test phase. The development of generative models enables current GZSL techniques to probe further into the semantic-visual…

Computer Vision and Pattern Recognition · Computer Science 2022-05-06 Dubing Chen , Yuming Shen , Haofeng Zhang , Philip H. S. Torr

The core task of recommender systems is to learn user preferences from historical user-item interactions. With the rapid development of large language models (LLMs), recent research has explored leveraging the reasoning capabilities of LLMs…

Information Retrieval · Computer Science 2025-10-28 Xiaoyu Kong , Junguang Jiang , Bin Liu , Ziru Xu , Han Zhu , Jian Xu , Bo Zheng , Jiancan Wu , Xiang Wang

Geospatial reasoning requires models to resolve complex spatial semantics and user intent into precise target locations for Earth observation. Recent progress has liberated the reasoning path from manual curation, allowing models to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Liang Yao , Fan Liu , Shengxiang Xu , Chuanyi Zhang , Rui Min , Shimin Di , Yuhui Zheng

Mainstream LLM research has primarily focused on enhancing their generative capabilities. However, even the most advanced LLMs experience uncertainty in their outputs, often producing varied results on different runs or when faced with…

Computation and Language · Computer Science 2024-07-17 Jihyun Janice Ahn , Ryo Kamoi , Lu Cheng , Rui Zhang , Wenpeng Yin

Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision. However, in many reasoning domains, the model must also validate generated tasks and…

Artificial Intelligence · Computer Science 2026-05-28 Bowen Wei , Nan Wang , Yuqing Zhou , Jinhao Pan , Ziwei Zhu

Recently, self-play fine-tuning (SPIN) has been proposed to adapt large language models to downstream applications with scarce expert-annotated data, by iteratively generating synthetic responses from the model itself. However, SPIN is…

Computation and Language · Computer Science 2026-01-14 Yibo Wang , Hai-Long Sun , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang , Lijun Zhang

Automatic Prompt Optimization (APO) improves large language model (LLM) performance by refining prompts for specific tasks. However, prior APO methods typically focus only on user prompts, rely on unstructured feedback, and require large…

Computation and Language · Computer Science 2025-09-26 Seungyoun Yi , Minsoo Khang , Sungrae Park

Feature transformation involves generating a new set of features from the original dataset to enhance the data's utility. In certain domains like material performance screening, dimensionality is large and collecting labels is expensive and…

Machine Learning · Computer Science 2025-05-01 Nanxu Gong , Xinyuan Wang , Wangyang Ying , Haoyue Bai , Sixun Dong , Haifeng Chen , Yanjie Fu

Reinforcement learning has become essential for strengthening the reasoning abilities of large language models, yet current exploration mechanisms remain fundamentally misaligned with how these models actually learn. Entropy bonuses and…

Machine Learning · Computer Science 2025-12-18 Zhenwen Liang , Sidi Lu , Wenhao Yu , Kishan Panaganti , Yujun Zhou , Haitao Mi , Dong Yu

Reinforcement learning substantially improves pretrained language models, but it remains understudied why critic-free methods such as PPO and GRPO work as well as they do, and when they should provide the largest gains. We develop a…

Machine Learning · Computer Science 2026-05-22 Arip Asadulaev , Daniil Ognev , Karim Salta , Martin Takac

Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding holds promise, instruction-tuned models frequently fail even in…

Computation and Language · Computer Science 2025-06-19 Shang Hong Sim , Tej Deep Pala , Vernon Toh , Hai Leong Chieu , Amir Zadeh , Chuan Li , Navonil Majumder , Soujanya Poria

Auto-evaluation is crucial for assessing response quality and offering feedback for model development. Recent studies have explored training large language models (LLMs) as generative judges to evaluate and critique other models' outputs.…

Computation and Language · Computer Science 2025-09-15 Peifeng Wang , Austin Xu , Yilun Zhou , Caiming Xiong , Shafiq Joty

Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Zhengxian Wu , Kai Shi , Chuanrui Zhang , Zirui Liao , Jun Yang , Ni Yang , Qiuying Peng , Luyuan Zhang , Hangrui Xu , Tianhuang Su , Zhenyu Yang , Haonan Lu , Haoqian Wang

Training large language models (LLMs) for non-verifiable tasks, such as creative writing, dialogue, and ethical reasoning, remains challenging due to the absence of ground-truth labels. While LLM-as-Judge approaches offer a scalable…

Computation and Language · Computer Science 2026-05-08 Yuan Sui , Bryan Hooi