English
Related papers

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

200 papers

Modern language models define distributions over strings, but downstream tasks often require different output formats. For instance, a model that generates byte-pair strings does not directly produce word-level predictions, and a DNA model…

Computation and Language · Computer Science 2026-03-09 Vésteinn Snæbjarnarson , Samuel Kiegeland , Tianyu Liu , Reda Boumasmoud , Ryan Cotterell , Tim Vieira

Estimating the log-likelihood of a given sentence under an autoregressive language model is straightforward: one can simply apply the chain rule and sum the log-likelihood values for each successive token. However, for masked language…

Computation and Language · Computer Science 2023-05-24 Carina Kauf , Anna Ivanova

Modern preference alignment techniques, such as Best-of-N (BoN) sampling, rely on reward models trained with pairwise comparison data. While effective at learning relative preferences, this paradigm fails to capture a signal of response…

Methodology · Statistics 2025-10-14 Hyung Gyu Rho , Sian Lee

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Computation and Language · Computer Science 2025-10-21 Mingye Zhu , Yi Liu , Zheren Fu , Yongdong Zhang , Zhendong Mao

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how…

Computation and Language · Computer Science 2020-11-13 Charles Welch , Jonathan K. Kummerfeld , Verónica Pérez-Rosas , Rada Mihalcea

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…

Computation and Language · Computer Science 2023-11-28 Haoyi Wu , Kewei Tu

We examine a naming game on an adaptive weighted network. A weight of connection for a given pair of agents depends on their communication success rate and determines the probability with which the agents communicate. In some cases,…

Statistical Mechanics · Physics 2012-08-10 Dorota Lipowska , Adam Lipowski

A wide body of evidence shows that human language processing difficulty is predicted by the information-theoretic measure surprisal, a word's negative log probability in context. However, it is still unclear how to best estimate these…

Computation and Language · Computer Science 2024-07-04 Tong Liu , Iza Škrjanec , Vera Demberg

Learning from human feedback has gained traction in fields like robotics and natural language processing in recent years. While prior works mostly rely on human feedback in the form of comparisons, language is a preferable modality that…

Robotics · Computer Science 2024-10-10 Zhaojing Yang , Miru Jun , Jeremy Tien , Stuart J. Russell , Anca Dragan , Erdem Bıyık

Numerous recent techniques for text style transfer characterize their approaches as variants of reinforcement learning and preference optimization. In this work, we consider the relationship between these approaches and a class of…

Computation and Language · Computer Science 2024-07-30 Shuai Liu , Jonathan May

The principle of rewarding a crowd for surprisingly common answers has been used in the literature for designing a number of truthful information elicitation mechanisms. A related method has also been proposed in the literature for better…

Machine Learning · Computer Science 2025-01-28 Naman Goel

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Computation and Language · Computer Science 2025-01-23 Yafu Li , Xuyang Hu , Xiaoye Qu , Linjie Li , Yu Cheng

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

Computation and Language · Computer Science 2025-05-27 Xiaochen Zhu , Caiqi Zhang , Tom Stafford , Nigel Collier , Andreas Vlachos

The paper presents a language model that develops syntactic structure and uses it to extract meaningful information from the word history, thus enabling the use of long distance dependencies. The model assigns probability to every joint…

Computation and Language · Computer Science 2007-05-23 Ciprian Chelba

In this paper a first attempt at deriving an improved performance measure for language models, the probability ratio measure (PRM) is described. In a proof of concept experiment, it is shown that PRM correlates better with recognition…

cmp-lg · Computer Science 2007-05-23 Joerg P. Ueberla

Diversity is an essential metric for evaluating the creativity of outputs generated by language models. Temperature-based sampling is a common strategy to increase diversity. However, for tasks that require high precision, e.g.,…

Machine Learning · Computer Science 2025-10-03 Sergey Troshin , Wafaa Mohammed , Yan Meng , Christof Monz , Antske Fokkens , Vlad Niculae

Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans. However, empirical evidence has been limited to experiments with highly simplified artificial languages, and whether…

Computation and Language · Computer Science 2025-02-19 Tianyang Xu , Tatsuki Kuribayashi , Yohei Oseki , Ryan Cotterell , Alex Warstadt

Recent works have revealed the great potential of speculative decoding in accelerating the autoregressive generation process of large language models. The success of these methods relies on the alignment between draft candidates and the…

Computation and Language · Computer Science 2025-09-15 Jikai Wang , Zhenxu Tian , Juntao Li , Qingrong Xia , Xinyu Duan , Zhefeng Wang , Baoxing Huai , Min Zhang

Selecting high-quality and diverse training samples from extensive datasets plays a crucial role in reducing training overhead and enhancing the performance of Large Language Models (LLMs). However, existing studies fall short in assessing…

Computation and Language · Computer Science 2025-10-14 Zhuo Li , Yuhao Du , Xiaoqi Jiao , Yiwen Guo , Yuege Feng , Xiang Wan , Anningzhe Gao , Jinpeng Hu

Synonyms and homonyms appear in all natural languages. We analyse their evolution within the framework of the signaling game. Agents in our model use reinforcement learning, where probabilities of selection of a communicated word or of its…

Physics and Society · Physics 2022-01-28 Dorota Lipowski , Adam Lipowski
‹ Prev 1 4 5 6 7 8 10 Next ›