English
Related papers

Related papers: Rubrics as an Attack Surface: Stealthy Preference …

200 papers

Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a…

Computation and Language · Computer Science 2025-09-03 Andong Hua , Kenan Tang , Chenhe Gu , Jindong Gu , Eric Wong , Yao Qin

Typical LLM responses tend to follow a default style, even though users often have distinct preferences regarding tone, verbosity, and formality that they do not explicitly state in their prompts. Evaluating whether personalization methods…

Computation and Language · Computer Science 2026-05-21 Philipp Spohn , Leander Girrbach , Zeynep Akata

Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations that limit domain…

Machine Learning · Computer Science 2026-05-20 Junjie Zhang , Guozheng Ma , Shunyu Liu , Zetian Hu , Yongcheng Jing , Ting-En Lin , Yongbin Li , Dacheng Tao

Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance…

Artificial Intelligence · Computer Science 2025-04-25 Yuran Li , Jama Hussein Mohamud , Chongren Sun , Di Wu , Benoit Boulet

Rubric-based evaluation is widely used in LLM benchmarks and training pipelines for open-ended, less verifiable tasks. While prior work has demonstrated the effectiveness of rubrics using downstream signals such as reinforcement learning…

Artificial Intelligence · Computer Science 2026-04-22 Zhengyang Qi , Charles Dickens , Derek Pham , Amanda Dsouza , Armin Parchami , Frederic Sala , Paroma Varma

As AI systems approach superhuman capabilities, scalable oversight increasingly relies on LLM-as-a-judge frameworks where models evaluate and guide each other's training. A core assumption is that binary preference labels provide only…

Machine Learning · Computer Science 2026-03-13 Isotta Magistrali , Frédéric Berdoz , Sam Dauncey , Roger Wattenhofer

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Cryptography and Security · Computer Science 2026-04-28 Yuansen Liu , Yixuan Tang , Anthony Kum Hoe Tun

Preference learning provides a promising solution to address the limitations of supervised fine-tuning (SFT) for code language models, where the model is not explicitly trained to differentiate between correct and incorrect code. Recent…

Computation and Language · Computer Science 2024-10-15 Dylan Zhang , Shizhe Diao , Xueyan Zou , Hao Peng

Large Language Models (LLMs) have exhibited strong mathematical reasoning prowess, tackling tasks ranging from basic arithmetic to advanced competition-level problems. However, frequently occurring subtle yet critical errors, such as…

Computation and Language · Computer Science 2025-05-28 Kaishuai Xu , Tiezheng Yu , Wenjun Hou , Yi Cheng , Chak Tou Leong , Liangyou Li , Xin Jiang , Lifeng Shang , Qun Liu , Wenjie Li

Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing…

Computation and Language · Computer Science 2026-05-28 Yuming , Huang , Yao Liu , Lei Wang , Junchen Wan

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Ya-Qi Yu , Hao Wang , Fangyu Hong , Xiangyang Qu , Gaojie Wu , Qiaoyu Luo , Nuo Xu , Huixin Wang , Wuheng Xu , Yongxin Liao , Zihao Chen , Haonan Li , Ziming Li , Dezhi Peng , Minghui Liao , Jihao Wu , Haoyu Ren , Dandan Tu

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…

Machine Learning · Computer Science 2025-03-06 Erfan Entezami , Ali Naseh

Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding…

Computation and Language · Computer Science 2024-10-10 Nuo Chen , Jiqun Liu , Xiaoyu Dong , Qijiong Liu , Tetsuya Sakai , Xiao-Ming Wu

The paradigm of LLM-as-a-judge relies on a critical assumption, namely that high inter-evaluator agreement indicates reliable and objective evaluation. We present two complementary findings that challenge this assumption. \textbf{First}, we…

Computation and Language · Computer Science 2026-03-12 Mingyang Song , Mao Zheng , Chenning Xu

Large language models (LLMs) are increasingly used as automatic evaluators in applications such as benchmarking, reward modeling, and self-refinement. Prior work highlights a potential self-preference bias where LLMs favor their own…

Computation and Language · Computer Science 2025-12-16 Wei-Lin Chen , Zhepei Wei , Xinyu Zhu , Shi Feng , Yu Meng

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…

Computation and Language · Computer Science 2024-04-10 Yue Xu , Wenjie Wang

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Computation and Language · Computer Science 2025-11-24 Ziqi Miao , Lijun Li , Yuan Xiong , Zhenhua Liu , Pengyu Zhu , Jing Shao

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu

Objective. Clinical AI documentation systems require evaluation methodologies that are clinically valid, economically viable, and sensitive to iterative changes. Methods requiring expert review per scoring instance are too slow and…

Artificial Intelligence · Computer Science 2026-04-28 Aaryan Shah , Andrew Hines , Alexia Downs , Denis Bajet , Paulius Mui , Fabiano Araujo , Laura Offutt , Aida Rutledge , Elizabeth Jimenez