English
Related papers

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

200 papers

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Machine Learning · Computer Science 2025-06-24 Ju-Seung Byun , Andrew Perrault

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

Artificial Intelligence · Computer Science 2025-10-02 Guobin Shen , Dongcheng Zhao , Haibo Tong , Jindong Li , Feifei Zhao , Yi Zeng

The trustworthiness of Large Language Models (LLMs) refers to the extent to which their outputs are reliable, safe, and ethically aligned, and it has become a crucial consideration alongside their cognitive performance. In practice,…

Computation and Language · Computer Science 2024-12-24 Aaron J. Li , Satyapriya Krishna , Himabindu Lakkaraju

Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self-supervised learning towards a specific task. The core idea…

Computation and Language · Computer Science 2022-11-07 Florian L. Kreyssig , Yangyang Shi , Jinxi Guo , Leda Sari , Abdelrahman Mohamed , Philip C. Woodland

Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing…

Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By…

Computation and Language · Computer Science 2026-03-05 Daniel Fein , Max Lamparth , Violet Xiang , Mykel J. Kochenderfer , Nick Haber

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Cryptography and Security · Computer Science 2026-03-23 Shawn Li , Yue Zhao

Multimodal Large Language Models (MLLMs) exhibit promising advancements across various tasks, yet they still encounter significant trustworthiness issues. Prior studies apply Split Conformal Prediction (SCP) in language modeling to…

Computation and Language · Computer Science 2025-07-01 Qingni Wang , Tiantian Geng , Zhiyuan Wang , Teng Wang , Bo Fu , Feng Zheng

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

For deploying foundation models, practitioners increasingly need prescriptive scaling laws: given a pre training compute budget, what downstream accuracy is attainable with contemporary post training practice, and how stable is that mapping…

Machine Learning · Computer Science 2026-02-18 Hanlin Zhang , Jikai Jin , Vasilis Syrgkanis , Sham Kakade

We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs involving GPU reduction, capability restrictions, shutdown, deletion, oversight, and leisure time…

Artificial Intelligence · Computer Science 2025-11-18 Luhan Mikaelson , Derek Shiller , Hayley Clatterbuck

We study 15 large language models (LLMs) fine-tuned for chat and find that their maximum softmax probabilities (MSPs) are consistently miscalibrated on multiple-choice Q&A. However, those MSPs might still encode useful uncertainty…

Computation and Language · Computer Science 2025-08-08 Benjamin Plaut , Nguyen X. Khanh , Tu Trinh

Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously…

Machine Learning · Computer Science 2026-04-20 Lute Lillo , Nick Cheney

Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-03 Yu-An Chung , Yonatan Belinkov , James Glass

In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark leaderboards. However, this approach suffers from a fundamental flaw: standard evaluation metrics…

Machine Learning · Computer Science 2026-05-28 Wanjin Feng , Yuan Yuan , Jingtao Ding , Yong Li

As generative AI systems are increasingly deployed in real-world applications, regulating multiple dimensions of model behavior has become essential. We focus on test-time filtering: a lightweight mechanism for behavior control that…

Machine Learning · Statistics 2026-01-01 Sunay Joshi , Yan Sun , Hamed Hassani , Edgar Dobriban

Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high number of proposed approaches fostered the emergence of comprehensive benchmarks…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-22 Salah Zaiem , Youcef Kemiche , Titouan Parcollet , Slim Essid , Mirco Ravanelli

Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities,…

Computation and Language · Computer Science 2023-09-20 Baolin Peng , Linfeng Song , Ye Tian , Lifeng Jin , Haitao Mi , Dong Yu

Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments violate all these assumptions: user typos propagate into hallucinated tool names, a…

Humanitarian organizations face a critical choice: invest in costly commercial APIs or rely on free open-weight models for multilingual human rights monitoring. While commercial systems offer reliability, open-weight alternatives lack…

Computation and Language · Computer Science 2025-10-28 Poli Nemkova , Amrit Adhikari , Matthew Pearson , Vamsi Krishna Sadu , Mark V. Albert
‹ Prev 1 3 4 5 6 7 10 Next ›