English
Related papers

Related papers: Consistency Training Helps Stop Sycophancy and Jai…

200 papers

Refusal training is widely used to prevent LLMs from generating harmful, undesirable, or illegal outputs. We reveal a curious generalization gap in the current refusal training approaches: simply reformulating a harmful request in the past…

Computation and Language · Computer Science 2025-04-21 Maksym Andriushchenko , Nicolas Flammarion

Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to generate intermediate reasoning steps before reaching the final…

Computation and Language · Computer Science 2025-04-15 Zuoli Tang , Junjie Ou , Kaiqin Hu , Chunwei Wu , Zhaoxin Huan , Chilin Fu , Xiaolu Zhang , Jun Zhou , Chenliang Li

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Machine Learning · Computer Science 2026-01-22 Song Lai , Haohan Zhao , Rong Feng , Changyi Ma , Wenzhuo Liu , Hongbo Zhao , Xi Lin , Dong Yi , Qingfu Zhang , Hongbin Liu , Gaofeng Meng , Fei Zhu

Machine-learning models demand periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly updated model may commit mistakes the previous model did not make. Such…

Machine Learning · Computer Science 2025-05-30 Daniele Angioni , Luca Demetrio , Maura Pintor , Luca Oneto , Davide Anguita , Battista Biggio , Fabio Roli

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

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training or metatag training survive such edits? We study model…

Self-consistency -- sampling multiple reasoning paths and selecting the most frequent answer -- was designed for an era when language models made frequent, unpredictable errors. This study argues that the technique has become increasingly…

Artificial Intelligence · Computer Science 2026-05-08 Chiyan Loo

Large language models (LLMs) have achieved strong performance across a wide range of tasks, but they are also prone to sycophancy, the tendency to agree with user statements regardless of validity. Previous research has outlined both the…

Computation and Language · Computer Science 2026-03-31 Bayan Abdullah Aldahlawi , A. B. M. Ashikur Rahman , Irfan Ahmad

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…

Machine Learning · Computer Science 2025-02-07 Sihui Dai , Christian Cianfarani , Arjun Bhagoji , Vikash Sehwag , Prateek Mittal

Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by reinforcing the correct goals, but alignment may not always succeed and can lead to unwanted side…

Machine Learning · Computer Science 2026-02-27 Bruce W. Lee , Chen Yueh-Han , Tomek Korbak

In this paper, we present our finding that prepending a Task-Agnostic Prefix Prompt (TAPP) to the input improves the instruction-following ability of various Large Language Models (LLMs) during inference. TAPP is different from canonical…

Computation and Language · Computer Science 2023-12-27 Seonghyeon Ye , Hyeonbin Hwang , Sohee Yang , Hyeongu Yun , Yireun Kim , Minjoon Seo

While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effectiveness in accurately adhering to instructions remains…

Computation and Language · Computer Science 2025-08-06 Chenyang Wang , Liang Wen , Shousheng Jia , Xiangzheng Zhang , Liang Xu

Sycophancy (overly agreeable or flattering behavior) poses a fundamental challenge for human-AI collaboration, particularly in high-stakes decision-making domains such as health, law, and education. A central difficulty in studying…

Artificial Intelligence · Computer Science 2026-05-05 Katherine Atwell , Pedram Heydari , Anthony Sicilia , Malihe Alikhani

Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize their input contexts, resulting in responses that are unfaithful…

Computation and Language · Computer Science 2024-09-18 Qingru Zhang , Xiaodong Yu , Chandan Singh , Xiaodong Liu , Liyuan Liu , Jianfeng Gao , Tuo Zhao , Dan Roth , Hao Cheng

The phenomena of in-context learning has typically been thought of as "learning from examples". In this work which focuses on Machine Translation, we present a perspective of in-context learning as the desired generation task maintaining…

Computation and Language · Computer Science 2023-05-08 Suzanna Sia , Kevin Duh

Instruction tuning has emerged as a paramount method for tailoring the behaviors of LLMs. Recent work has unveiled the potential for LLMs to achieve high performance through fine-tuning with a limited quantity of high-quality instruction…

Artificial Intelligence · Computer Science 2025-04-01 Qiang Wang , Dawei Feng , Xu Zhang , Ao Shen , Yang Xu , Bo Ding , Huaimin Wang

This paper investigates the potentials of Large Language Models (LLMs) as adaptive tutors in the context of second-language learning. In particular, we evaluate whether system prompting can reliably constrain LLMs to generate only text…

Computation and Language · Computer Science 2025-06-10 Mina Almasi , Ross Deans Kristensen-McLachlan

Large language models (LLMs) are increasingly applied in educational, clinical, and professional settings, but their tendency for sycophancy -- prioritizing user agreement over independent reasoning -- poses risks to reliability. This study…

Artificial Intelligence · Computer Science 2025-09-22 Aaron Fanous , Jacob Goldberg , Ank A. Agarwal , Joanna Lin , Anson Zhou , Roxana Daneshjou , Sanmi Koyejo
‹ Prev 1 3 4 5 6 7 10 Next ›