English
Related papers

Related papers: ContraPrompt: Contrastive Prompt Optimization via …

200 papers

Recently, prompt tuning methods for pre-trained models have demonstrated promising performance in Class Incremental Learning (CIL). These methods typically involve learning task-specific prompts and predicting the task ID to select the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Qiwei Li , Jiahuan Zhou

Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain inefficient. Standard approaches retain only the single highest-reward trajectory, discarding…

Artificial Intelligence · Computer Science 2026-04-14 Peiyang Liu , Zhirui Chen , Xi Wang , Di Liang , Youru Li , Zhi Cai , Wei Ye

We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences describing intermediate reasoning steps towards…

Computation and Language · Computer Science 2023-01-31 Yao Fu , Hao Peng , Ashish Sabharwal , Peter Clark , Tushar Khot

LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial…

Artificial Intelligence · Computer Science 2026-03-11 Arash Shahmansoori

Despite the success of chain of thought in enhancing language model reasoning, the underlying process remains less well understood. Although logically sound reasoning appears inherently crucial for chain of thought, prior studies…

Computation and Language · Computer Science 2023-11-17 Yew Ken Chia , Guizhen Chen , Luu Anh Tuan , Soujanya Poria , Lidong Bing

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that…

Large Language Models (LLMs) have achieved impressive performance across various reasoning tasks. However, even state-of-the-art LLMs such as ChatGPT are prone to logical errors during their reasoning processes. Existing solutions, such as…

Computation and Language · Computer Science 2024-03-25 Chi Hu , Yuan Ge , Xiangnan Ma , Hang Cao , Qiang Li , Yonghua Yang , Tong Xiao , Jingbo Zhu

Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in domains like mathematical reasoning and coding, typically…

Computation and Language · Computer Science 2025-02-17 Fangkai Jiao , Geyang Guo , Xingxing Zhang , Nancy F. Chen , Shafiq Joty , Furu Wei

Inspired by advances in LLMs, reasoning-enhanced sequential recommendation performs multi-step deliberation before making final predictions, unlocking greater potential for capturing user preferences. However, current methods are…

Information Retrieval · Computer Science 2025-12-17 Yifan Shao , Peilin Zhou , Shoujin Wang , Weizhi Zhang , Xu Cai , Sunghun Kim

In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks only focus on final answers. Two fundamental questions persist: 1) how consistent is the…

Computation and Language · Computer Science 2024-10-22 Ziyi Liu , Soumya Sanyal , Isabelle Lee , Yongkang Du , Rahul Gupta , Yang Liu , Jieyu Zhao

Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on long, multi-step problems, leading to…

Artificial Intelligence · Computer Science 2026-04-28 Shuxu Chen , Yitian Zhou , Jiaquan Zhang , Haoyu Bian , Aming Wu , Sungyoung Lee , Chaoning Zhang , Hyundong Shin

Automated prompt optimization methods (e.g., DSpy, TextGrad) can substantially improve the performance of large language model (LLM), however, their generalization ability across different tasks remains underperformed. In practice, the…

Computation and Language · Computer Science 2026-05-27 Shuzhi Gong , Hechuan Wen

Recommender systems are frequently challenged by the data sparsity problem. One approach to mitigate this issue is through cross-domain recommendation techniques. In a cross-domain context, sharing knowledge between domains can enhance the…

Information Retrieval · Computer Science 2023-11-06 Zixuan Yi , Iadh Ounis , Craig Macdonald

Prompting methods play a crucial role in enhancing the capabilities of pre-trained large language models (LLMs). We explore how contrastive prompting (CP) significantly improves the ability of large language models to perform complex…

Computation and Language · Computer Science 2026-03-06 Liang Yao

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

Artificial Intelligence · Computer Science 2025-10-14 Martina G. Vilas , Safoora Yousefi , Besmira Nushi , Eric Horvitz , Vidhisha Balachandran

Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization…

Machine Learning · Computer Science 2025-11-18 Fei Song , Yi Li , Rui Wang , Jiahuan Zhou , Changwen Zheng , Jiangmeng Li

Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO,…

Computation and Language · Computer Science 2026-03-26 Rahul Singhal , Pradyumna Tambwekar , Karime Maamari

Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necessitates costly post-processing. To tackle this, we propose…

Artificial Intelligence · Computer Science 2025-10-28 Kaitong Cai , Jusheng Zhang , Yijia Fan , Jing Yang , Keze Wang

Logical reasoning is of vital importance to natural language understanding. Previous studies either employ graph-based models to incorporate prior knowledge about logical relations, or introduce symbolic logic into neural models through…

Computation and Language · Computer Science 2022-03-02 Fangkai Jiao , Yangyang Guo , Xuemeng Song , Liqiang Nie

Prompt-tuning has emerged as a promising method for adapting pre-trained models to downstream tasks or aligning with human preferences. Prompt learning is widely used in NLP but has limited applicability to RL due to the complex physical…

Machine Learning · Computer Science 2023-05-17 Shengchao Hu , Li Shen , Ya Zhang , Dacheng Tao