English
Related papers

Related papers: BLOCK-EM: Preventing Emergent Misalignment via Lat…

200 papers

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignment: residual connections tie activations to the current…

Computation and Language · Computer Science 2026-03-03 Jonathan Lys , Vincent Gripon , Bastien Pasdeloup , Axel Marmoret , Lukas Mauch , Fabien Cardinaux , Ghouthi Boukli Hacene

Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted parameter modifications, with meta-learning-based model editing…

Computation and Language · Computer Science 2026-01-30 Xiaopeng Li , Shasha Li , Xi Wang , Shezheng Song , Bin Ji , Shangwen Wang , Jun Ma , Xiaodong Liu , Mina Liu , Jie Yu

Misalignment in Large Language Models (LLMs) refers to the failure to simultaneously satisfy safety, value, and cultural dimensions, leading to behaviors that diverge from human expectations in real-world settings where these dimensions…

Computation and Language · Computer Science 2026-02-12 Usman Naseem , Gautam Siddharth Kashyap , Ebad Shabbir , Sushant Kumar Ray , Abdullah Mohammad , Rafiq Ali

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF). In…

Artificial Intelligence · Computer Science 2025-06-18 Jiahao Yu , Haozheng Luo , Jerry Yao-Chieh Hu , Wenbo Guo , Han Liu , Xinyu Xing

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook…

Computation and Language · Computer Science 2024-06-10 Yikun Wang , Rui Zheng , Liang Ding , Qi Zhang , Dahua Lin , Dacheng Tao

The requirement of high spectrum efficiency puts forward higher requirements on frame synchronization (FS) in wireless communication systems. Meanwhile, a large number of nonlinear devices or blocks will inevitably cause nonlinear…

Signal Processing · Electrical Eng. & Systems 2021-03-30 Chaojin Qing , Wang Yu , Shuhai Tang , Chuangui Rao , Jiafan Wang

Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Dongxu Li , Junnan Li , Hongdong Li , Juan Carlos Niebles , Steven C. H. Hoi

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

Pretraining of large language models is not only expensive but also prone to certain training instabilities. A specific instability that often occurs at the end of training is output logit divergence. The most widely used mitigation…

Machine Learning · Computer Science 2026-04-03 Felix Stollenwerk , Anna Lokrantz , Niclas Hertzberg

Edge detection is among the most fundamental vision problems for its role in perceptual grouping and its wide applications. Recent advances in representation learning have led to considerable improvements in this area. Many state of the art…

Computer Vision and Pattern Recognition · Computer Science 2018-10-29 Zhiding Yu , Weiyang Liu , Yang Zou , Chen Feng , Srikumar Ramalingam , B. V. K. Vijaya Kumar , Jan Kautz

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Computation and Language · Computer Science 2024-12-23 Barry Menglong Yao , Qifan Wang , Lifu Huang

Blocking is a mechanism to improve the efficiency of Entity Resolution (ER) which aims to quickly prune out all non-matching record pairs. However, depending on the distributions of entity cluster sizes, existing techniques can be either…

Databases · Computer Science 2021-03-17 Sainyam Galhotra , Donatella Firmani , Barna Saha , Divesh Srivastava

Despite investments in improving model safety, studies show that misaligned capabilities remain latent in safety-tuned models. In this work, we shed light on the mechanics of this phenomenon. First, we show that even when model generations…

Computation and Language · Computer Science 2024-08-14 Asma Ghandeharioun , Ann Yuan , Marius Guerard , Emily Reif , Michael A. Lepori , Lucas Dixon

An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors…

Computation and Language · Computer Science 2024-06-04 Yotam Wolf , Noam Wies , Oshri Avnery , Yoav Levine , Amnon Shashua

The attention mechanism has become a cornerstone of modern deep learning architectures, where keys and values are typically derived from the same underlying sequence or representation. This work explores a less conventional scenario, when…

Machine Learning · Computer Science 2025-10-01 Bissmella Bahaduri , Hicham Talaoubrid , Fangchen Feng , Zuheng Ming , Anissa Mokraoui

Weight-perturbation evolution strategies (ES) can fine-tune billion-parameter language models with surprisingly small populations (e.g., $N\!\approx\!30$), contradicting classical zeroth-order curse-of-dimensionality intuition. We also…

Machine Learning · Computer Science 2026-02-03 Qiyao Liang , Jinyeop Song , Yizhou Liu , Jeff Gore , Ila Fiete , Risto Miikkulainen , Xin Qiu

Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level behavior under model rollouts. We introduce a feature-matching…

Machine Learning · Computer Science 2026-03-17 Samy Jelassi , Mujin Kwun , Rosie Zhao , Yuanzhi Li , Nicolo Fusi , Yilun Du , Sham M. Kakade , Carles Domingo-Enrich

Self-reflection -- the ability of a large language model (LLM) to revisit, evaluate, and revise its own reasoning -- has recently emerged as a powerful behavior enabled by reinforcement learning with verifiable rewards (RLVR). While…

Machine Learning · Computer Science 2025-06-17 Xudong Zhu , Jiachen Jiang , Mohammad Mahdi Khalili , Zhihui Zhu

Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Yanyun Wang , Qingqing Ye , Li Liu , Zi Liang , Haibo Hu