中文
相关论文

相关论文: AIR: A Systematic Analysis of Annotations, Instruc…

200 篇论文

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

计算与语言 · 计算机科学 2024-12-23 Joongwon Kim , Anirudh Goyal , Aston Zhang , Bo Xiong , Rui Hou , Melanie Kambadur , Dhruv Mahajan , Hannaneh Hajishirzi , Liang Tan

LLMs achieve remarkable multi-step reasoning capabilities, yet effectively transferring these skills via post-training distillation remains challenging. Existing data selection methods, ranging from manual curation to heuristics based on…

计算与语言 · 计算机科学 2025-12-16 Jinrui Liu , Jeff Wu , Xuanguang Pan , Gavin Cheung , Shuai Ma , Chongyang Tao

This paper studies Automated Instruction Revision (AIR), a rule-induction-based method for adapting large language models (LLMs) to downstream tasks using limited task-specific examples. We position AIR within the broader landscape of…

计算与语言 · 计算机科学 2026-04-13 Solomiia Bilyk , Volodymyr Getmanskyi , Taras Firman

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

机器学习 · 计算机科学 2025-07-15 Hoang Anh Just , Ming Jin , Anit Sahu , Huy Phan , Ruoxi Jia

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…

计算与语言 · 计算机科学 2025-06-05 Honggen Zhang , Xufeng Zhao , Igor Molybog , June Zhang

Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to select worth-annotating response pairs for cost-efficient annotation while achieving…

计算与语言 · 计算机科学 2024-10-14 Sen Yang , Leyang Cui , Deng Cai , Xinting Huang , Shuming Shi , Wai Lam

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense feedback annotations are expensive to acquire and integrate, sparse feedback presents a structural design…

机器学习 · 计算机科学 2024-02-07 Hritik Bansal , John Dang , Aditya Grover

While the efficacy of deep learning models heavily relies on data, gathering and annotating data for specific tasks, particularly when addressing novel or sensitive subjects lacking relevant datasets, poses significant time and resource…

计算机视觉与模式识别 · 计算机科学 2025-06-25 Quang-Binh Nguyen , Trong-Vu Hoang , Ngoc-Do Tran , Tam V. Nguyen , Minh-Triet Tran , Trung-Nghia Le

Continual learning enables AI models to learn new data sequentially without retraining in real-world scenarios. Most existing methods assume the training data are balanced, aiming to reduce the catastrophic forgetting problem that models…

机器学习 · 计算机科学 2024-08-21 Di Fang , Yinan Zhu , Runze Fang , Cen Chen , Ziqian Zeng , Huiping Zhuang

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

人工智能 · 计算机科学 2026-05-12 Katarzyna Kobalczyk , Mihaela van der Schaar

Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when the same intent is wrapped in adversarial wording. We suggest…

计算与语言 · 计算机科学 2026-05-21 Yixu Wang , Yang Yao , Xin Wang , Yifeng Gao , Yan Teng , Xingjun Ma , Yingchun Wang

Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we…

机器学习 · 计算机科学 2025-03-05 Dongyoung Kim , Kimin Lee , Jinwoo Shin , Jaehyung Kim

Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and inefficient-motivating the need for efficient data selection methods that reduce annotation costs…

计算与语言 · 计算机科学 2026-04-21 Seohyeong Lee , Eunwon Kim , Hwaran Lee , Buru Chang

Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…

计算与语言 · 计算机科学 2025-03-10 Xuanqing Liu , Luyang Kong , Wei Niu , Afshin Khashei , Belinda Zeng , Steve Johnson , Jon Jay , Davor Golac , Matt Pope

Human-annotated preference data play an important role in aligning large language models (LLMs). In this paper, we study two connected questions: how to monitor the quality of human preference annotators and how to incentivize them to…

机器学习 · 计算机科学 2026-04-08 Shang Liu , Hanzhao Wang , Zhongyao Ma , Xiaocheng Li

Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use, the way preference-based learning is applied varies wildly,…

Evolutionary Algorithms (EAs) employ random or simplistic selection methods, limiting their exploration of solution spaces and convergence to optimal solutions. The randomness in performing crossover or mutations may limit the model's…

神经与进化计算 · 计算机科学 2025-03-06 Shady Ali , Mahmoud Ashraf , Seif Hegazy , Fatty Salem , Hoda Mokhtar , Mohamed Medhat Gaber , Mohamed Taher Alrefaie

In this work, we introduce a methodology for alignment designed to enhance the ability of large language models (LLMs) to articulate their reasoning (self-explanation) even in the absence of annotated rationale explanations. Our alignment…

人工智能 · 计算机科学 2024-10-18 Luis Felipe Villa-Arenas , Ata Nizamoglu , Qianli Wang , Sebastian Möller , Vera Schmitt

Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences. While pre-training remains out of reach for most researchers due to the compute required, fine-tuning has…

计算与语言 · 计算机科学 2024-06-10 Megh Thakkar , Quentin Fournier , Matthew D Riemer , Pin-Yu Chen , Amal Zouaq , Payel Das , Sarath Chandar
‹ 上一页 1 2 3 10 下一页 ›