English
Related papers

Related papers: A Probability--Quality Trade-off in Aligned Langua…

200 papers

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

Large language models achieve strong performance on many language tasks, yet it remains unclear whether they integrate world knowledge with syntactic structure in a human-like, structure-sensitive way during ambiguity resolution. We test…

Computation and Language · Computer Science 2026-04-21 Sercan Karakaş

The staggering feats of AI systems have brought to attention the topic of AI Alignment: aligning a "superintelligent" AI agent's actions with humanity's interests. Many existing frameworks/algorithms in alignment study the problem on a…

Machine Learning · Computer Science 2024-10-22 Hong Jun Jeon , Benjamin Van Roy

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Computation and Language · Computer Science 2024-12-25 Shuzhang Cai , Twumasi Mensah-Boateng , Xander Kuksov , Jing Yuan , Shaojie Tang

Large language models (LLMs) are increasingly deployed via public-facing interfaces to interact with millions of users, each with diverse preferences. Despite this, preference tuning of LLMs predominantly relies on reward models trained…

Computation and Language · Computer Science 2024-12-06 Vishakh Padmakumar , Chuanyang Jin , Hannah Rose Kirk , He He

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

Artificial Intelligence · Computer Science 2026-05-27 Dongyoon Hahm , Dylan Hadfield-Menell , Kimin Lee

In this paper, we present a probabilistic adaptation of an Assume/Guarantee contract formalism. For the sake of generality, we assume that the extended state machines used in the contracts and implementations define sets of runs on a given…

Performance · Computer Science 2009-04-20 Benoît Delahaye , Benoît Caillaud

Compositionality is a hallmark of human language that not only enables linguistic generalization, but also potentially facilitates acquisition. When simulating language emergence with neural networks, compositionality has been shown to…

Computation and Language · Computer Science 2023-05-23 Emily Cheng , Mathieu Rita , Thierry Poibeau

Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model's prediction, it is still unclear how prior words affect the model's decision throughout…

Computation and Language · Computer Science 2023-05-23 Javier Ferrando , Gerard I. Gállego , Ioannis Tsiamas , Marta R. Costa-jussà

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human…

Machine Learning · Computer Science 2024-05-24 Andi Peng , Yuying Sun , Tianmin Shu , David Abel

The described tagger is based on a hidden Markov model and uses tags composed of features such as part-of-speech, gender, etc. The contextual probability of a tag (state transition probability) is deduced from the contextual probabilities…

cmp-lg · Computer Science 2008-02-03 Andre Kempe

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Computation and Language · Computer Science 2025-09-16 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference. In place of human users, a second language model can be used as an evaluator,…

Computation and Language · Computer Science 2024-07-08 Jane Pan , He He , Samuel R. Bowman , Shi Feng

We investigate the performance of large language models on repetitive deterministic prediction tasks and study how the sequence accuracy rate scales with output length. Each such task involves repeating the same operation n times. Examples…

Artificial Intelligence · Computer Science 2025-11-25 Wanda Hou , Leon Zhou , Hong-Ye Hu , Yubei Chen , Yi-Zhuang You , Xiao-Liang Qi

Selectional preference learning methods have usually focused on word-to-class relations, e.g., a verb selects as its subject a given nominal class. This papers extends previous statistical models to class-to-class preferences, and presents…

Computation and Language · Computer Science 2007-05-23 E. Agirre , D. Martinez

Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on human annotations provided by a select cohort of…

Artificial Intelligence · Computer Science 2024-05-31 Dexun Li , Cong Zhang , Kuicai Dong , Derrick Goh Xin Deik , Ruiming Tang , Yong Liu

In this article, we investigate the alignment of Large Language Models according to human preferences. We discuss the features of training a Preference Model, which simulates human preferences, and the methods and details we found essential…

Machine Learning · Computer Science 2024-10-03 Alexey Kutalev , Sergei Markoff

Learning reward models from human preference datasets and subsequently optimizing language models via reinforcement learning has emerged as a fundamental paradigm for aligning LLMs with human preferences. The performance of the reward model…

Computation and Language · Computer Science 2025-06-12 Wenjie Qiu , Yi-Chen Li , Xuqin Zhang , Tianyi Zhang , Yihang Zhang , Zongzhang Zhang , Yang Yu

Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch between pre-collected offline preference data and the…

Computation and Language · Computer Science 2026-03-02 Junming Yang , Ning Xu , Biao Liu , Shiqi Qiao , Xin Geng

Although language model scores are often treated as probabilities, their reliability as probability estimators has mainly been studied through calibration, overlooking other aspects. In particular, it is unclear whether language models…

Computation and Language · Computer Science 2024-10-01 Eitan Wagner , Yuli Slavutsky , Omri Abend