English
Related papers

Related papers: Alignment at Pre-training! Towards Native Alignmen…

200 papers

Large Language Models (LLMs) excel at providing information acquired during pretraining on large-scale corpora and following instructions through user prompts. This study investigates whether the quality of LLM responses varies depending on…

Computation and Language · Computer Science 2025-11-19 Manon Reusens , Philipp Borchert , Jochen De Weerdt , Bart Baesens

Recent work exploring the capabilities of pre-trained large language models (LLMs) has demonstrated their ability to act as general pattern machines by completing complex token sequences representing a wide array of tasks, including…

Computers and Society · Computer Science 2024-03-25 Seyed Parsa Neshaei , Richard Lee Davis , Adam Hazimeh , Bojan Lazarevski , Pierre Dillenbourg , Tanja Käser

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper investigates whether LLMs, like humans, struggle with reverse…

Computation and Language · Computer Science 2025-02-25 Sicheng Yu , Yuanchen Xu , Cunxiao Du , Yanying Zhou , Minghui Qiu , Qianru Sun , Hao Zhang , Jiawei Wu

Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and alignment choices. While pretraining encourages models to exploit all available…

Software Engineering · Computer Science 2025-12-25 Oussama Ben Sghaier , Kevin Delcourt , Houari Sahraoui

While brain-aligned large language models (LLMs) have garnered attention for their potential as cognitive models and for potential for enhanced safety and trustworthiness in AI, the role of this brain alignment for linguistic competence…

Computation and Language · Computer Science 2026-03-25 Gabriele Merlin , Mariya Toneva

Post-training alignment has increasingly become a crucial factor in enhancing the usability of language models (LMs). However, the strength of alignment varies depending on individual preferences. This paper proposes a method to incorporate…

Computation and Language · Computer Science 2026-01-13 Wenhong Zhu , Weinan Zhang , Rui Wang

Unsupervised multitask pre-training has been the critical method behind the recent success of language models (LMs). However, supervised multitask learning still holds significant promise, as scaling it in the post-training stage trends…

Computation and Language · Computer Science 2024-12-02 Daixuan Cheng , Yuxian Gu , Shaohan Huang , Junyu Bi , Minlie Huang , Furu Wei

Large language models (LLMs) perform strongly on many NLP tasks, but their ability to produce explicit linguistic structure remains unclear. We evaluate instruction-tuned LLMs on two structured prediction tasks for Standard Arabic:…

Computation and Language · Computer Science 2026-03-18 Mohamed Adel , Bashar Alhafni , Nizar Habash

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead…

Computation and Language · Computer Science 2025-12-22 Kangwei Liu , Mengru Wang , Yujie Luo , Lin Yuan , Mengshu Sun , Lei Liang , Zhiqiang Zhang , Jun Zhou , Bryan Hooi , Shumin Deng

Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness. In this paper, we argue for the importance of alignment for \emph{honesty}, ensuring that LLMs proactively refuse to…

Computation and Language · Computer Science 2024-10-29 Yuqing Yang , Ethan Chern , Xipeng Qiu , Graham Neubig , Pengfei Liu

While significant progress has been made in benchmarking Large Language Models (LLMs) across various tasks, there is a lack of comprehensive evaluation of their abilities in responding to multi-turn instructions in less-commonly tested…

Computation and Language · Computer Science 2023-10-24 Sabri Boughorbel , Majd Hawasly

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Computation and Language · Computer Science 2024-01-25 Lingfeng Shen , Weiting Tan , Sihao Chen , Yunmo Chen , Jingyu Zhang , Haoran Xu , Boyuan Zheng , Philipp Koehn , Daniel Khashabi

Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture-independent…

Computation and Language · Computer Science 2025-02-11 Yumeng Wang , Zhiyuan Fan , Qingyun Wang , May Fung , Heng Ji

Are Large language models (LLMs) temporally grounded? Since LLMs cannot perceive and interact with the environment, it is impossible to answer this question directly. Instead, we provide LLMs with textual narratives and probe them with…

Computation and Language · Computer Science 2023-11-17 Yifu Qiu , Zheng Zhao , Yftah Ziser , Anna Korhonen , Edoardo M. Ponti , Shay B. Cohen

Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training…

Computation and Language · Computer Science 2023-05-09 Yangyi Chen , Lifan Yuan , Ganqu Cui , Zhiyuan Liu , Heng Ji

The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constraints either in the…

Computation and Language · Computer Science 2025-04-28 Leitian Tao , Yixuan Li

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Artificial Intelligence · Computer Science 2025-02-18 Yingshui Tan , Yilei Jiang , Yanshi Li , Jiaheng Liu , Xingyuan Bu , Wenbo Su , Xiangyu Yue , Xiaoyong Zhu , Bo Zheng

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common…

Computation and Language · Computer Science 2024-01-09 Chen-An Li , Hung-Yi Lee

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Computation and Language · Computer Science 2024-10-04 Xiao Yu , Qingyang Wu , Yu Li , Zhou Yu