English
Related papers

Related papers: Quantifying Self-Preservation Bias in Large Langua…

200 papers

Scalable oversight studies methods of training and evaluating AI systems in domains where human judgment is unreliable or expensive, such as scientific research and software engineering in complex codebases. Most work in this area has…

Machine Learning · Computer Science 2024-10-22 Alex Mallen , Nora Belrose

The Adversarial Humanities Benchmark (AHB) evaluates whether model safety refusals survive a shift away from familiar harmful prompt forms. Starting from harmful tasks drawn from MLCommons AILuminate, the benchmark rewrites the same…

Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicitly mark the source of each piece of context. While these tags are essential for instruction…

Computation and Language · Computer Science 2026-04-21 Xu Pan , Jingxuan Fan , Zidi Xiong , Ely Hahami , Jorin Overwiening , Ziqian Xie

Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase both. For instance, repeated sampling has been shown to…

Artificial Intelligence · Computer Science 2025-10-08 Joshua Kazdan , Rylan Schaeffer , Youssef Allouah , Colin Sullivan , Kyssen Yu , Noam Levi , Sanmi Koyejo

Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators. Yet such simulators are typically evaluated by output…

Computation and Language · Computer Science 2026-05-14 Heejin Do , Shashank Sonkar , Mrinmaya Sachan

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative…

Artificial Intelligence · Computer Science 2025-09-18 Licheng Pan , Yongqi Tong , Xin Zhang , Xiaolu Zhang , Jun Zhou , Zhixuan Chu

Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language models could support such practice by simulating students with known skill components, enabling…

Computation and Language · Computer Science 2026-05-26 Alexander Apartsin , Omri Sason , Yehudit Aperstein

LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance…

Artificial Intelligence · Computer Science 2026-05-29 Johannes Moll , Jean-Philippe Corbeil , Jiazhen Pan , Martin Hadamitzky , Daniel Rueckert , Lisa Adams , Keno Bressem

Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). The selection often depends on the initial model fit on labeled data. Early overfitting might thus be propagated to the final model by selecting…

Machine Learning · Statistics 2023-06-27 Julian Rodemann , Jann Goschenhofer , Emilio Dorigatti , Thomas Nagler , Thomas Augustin

Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety,…

Artificial Intelligence · Computer Science 2025-05-27 Baihui Zheng , Boren Zheng , Kerui Cao , Yingshui Tan , Zhendong Liu , Weixun Wang , Jiaheng Liu , Jian Yang , Wenbo Su , Xiaoyong Zhu , Bo Zheng , Kaifu Zhang

Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward model to provide feedback for on-policy sampling responses.…

Machine Learning · Computer Science 2024-05-24 Yuanzhao Zhai , Zhuo Zhang , Kele Xu , Hanyang Peng , Yue Yu , Dawei Feng , Cheng Yang , Bo Ding , Huaimin Wang

Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accuracy on benchmarks, these models produce confident hallucinations, even when wrong answers carry…

Machine Learning · Computer Science 2025-11-25 Mohamad Amin Mohamadi , Tianhao Wang , Zhiyuan Li

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Computation and Language · Computer Science 2024-05-07 Yuval Reif , Roy Schwartz

Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or proportionally represent (Distributional) diverse human values. We argue that aggregation…

Artificial Intelligence · Computer Science 2026-05-15 Varad Vishwarupe , Nigel Shadbolt , Marina Jirotka

Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…

Machine Learning · Computer Science 2024-02-21 Siyuan Li , Weiyang Jin , Zedong Wang , Fang Wu , Zicheng Liu , Cheng Tan , Stan Z. Li

Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three…

Computation and Language · Computer Science 2026-01-21 Benaya Trabelsi , Jonathan Shaki , Sarit Kraus

Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) are the two dominant paradigms for enhancing Large Language Model (LLM) performance on downstream tasks. While RL generally preserves broader model capabilities (retention) better…

Machine Learning · Computer Science 2026-02-04 Rana Muhammad Shahroz Khan , Zijie Liu , Zhen Tan , Charles Fleming , Tianlong Chen

From school playgrounds to corporate boardrooms, status hierarchies -- rank orderings based on respect and perceived competence -- are universal features of human social organization. Language models trained on human-generated text…

Human-Computer Interaction · Computer Science 2026-01-27 Emilio Barkett

We consider the problem of estimating the false-/ true-positive-rate (FPR/TPR) for a binary classification model when there are incorrect labels (label noise) in the validation set. Our motivating application is fraud prevention where…

Machine Learning · Computer Science 2023-08-08 Justin Tittelfitz

Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representations. However, whether these suppressed representations can affect model outputs - and…

Artificial Intelligence · Computer Science 2026-05-18 Jagdish Tripathy , Marcus Buckmann