English
Related papers

Related papers: Contextual Temperature for Language Modeling

200 papers

Modern graph-based syntactic dependency parsers operate by predicting, for each token within a sentence, a probability distribution over its possible syntactic heads (i.e., all other tokens) and then extracting a maximum spanning tree from…

Computation and Language · Computer Science 2021-06-16 Stefan Grünewald

Temperature scaling is a popular technique for tuning the sharpness of a model distribution. It is used extensively for sampling likely generations and calibrating model uncertainty, and even features as a controllable parameter to many…

Machine Learning · Computer Science 2023-10-03 Andy Shih , Dorsa Sadigh , Stefano Ermon

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are…

Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an…

Computation and Language · Computer Science 2025-02-26 Fangyuan Yu

A central idea of knowledge distillation is to expose relational structure embedded in the teacher's weights for the student to learn, which is often facilitated using a temperature parameter. Despite its widespread use, there remains…

Machine Learning · Computer Science 2026-03-05 Logan Frank , Jim Davis

In this research study, we empirically investigate the effect of sampling temperature on the performance of Large Language Models (LLMs) on various problem-solving tasks. We created a multiple-choice question-and-answer (MCQA) exam by…

Computation and Language · Computer Science 2025-03-17 Matthew Renze , Erhan Guven

Humans often communicate by using imprecise language, suggesting that fuzzy concepts with unclear boundaries are prevalent in language use. In this paper, we test the extent to which models trained to capture the distributional statistics…

Computation and Language · Computer Science 2021-04-23 Kanishka Misra , Julia Taylor Rayz

Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic…

Computation and Language · Computer Science 2019-04-29 Nelson F. Liu , Matt Gardner , Yonatan Belinkov , Matthew E. Peters , Noah A. Smith

The sampling temperature, a critical hyperparameter in large language models (LLMs), modifies the logits before the softmax layer, thereby reshaping the distribution of output tokens. Recent studies have challenged the Stochastic Parrots…

Computation and Language · Computer Science 2025-06-10 Lujun Li , Lama Sleem , Niccolo' Gentile , Geoffrey Nichil , Radu State

It is now well known that neural networks can be wrong with high confidence in their predictions, leading to poor calibration. The most common post-hoc approach to compensate for this is to perform temperature scaling, which adjusts the…

Computer Vision and Pattern Recognition · Computer Science 2022-07-25 Tom Joy , Francesco Pinto , Ser-Nam Lim , Philip H. S. Torr , Puneet K. Dokania

Training large language representation models has become a standard in the natural language processing community. This allows for fine tuning on any number of specific tasks, however, these large high capacity models can continue to train…

Computation and Language · Computer Science 2020-04-09 Kristjan Arumae , Parminder Bhatia

Scaling model sizes to scale performance has worked remarkably well for the current large language models paradigm. The research and empirical findings of various scaling studies led to novel scaling results and laws that guides subsequent…

Recently, Large Language Models (LLMs) have demonstrated outstanding performance across a wide range of downstream language tasks. Temperature sampling is a commonly used decoding strategy for LLMs' generation process. However, a fixed…

Computation and Language · Computer Science 2024-04-04 Shimao Zhang , Yu Bao , Shujian Huang

Pretrained multilingual large language models have typically used heuristic temperature-based sampling to balance between different languages. However previous work has not systematically evaluated the efficacy of different pretraining…

Computation and Language · Computer Science 2023-04-19 Hyung Won Chung , Noah Constant , Xavier Garcia , Adam Roberts , Yi Tay , Sharan Narang , Orhan Firat

In this paper, we study the post-hoc calibration of modern neural networks, a problem that has drawn a lot of attention in recent years. Many calibration methods of varying complexity have been proposed for the task, but there is no…

Machine Learning · Computer Science 2022-08-02 Sergio A. Balanya , Juan Maroñas , Daniel Ramos

Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task…

Computation and Language · Computer Science 2023-11-14 Jin Myung Kwak , Minseon Kim , Sung Ju Hwang

Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various domains. Recent research has identified that tokens within LLMs…

Computation and Language · Computer Science 2025-10-13 Haomin Zhuang , Yujun Zhou , Taicheng Guo , Yue Huang , Fangxu Liu , Kai Song , Xiangliang Zhang

Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming…

Software Engineering · Computer Science 2023-12-29 Yuqi Zhu , Jia Li , Ge Li , YunFei Zhao , Jia Li , Zhi Jin , Hong Mei

Language understanding (LU) and dialogue policy learning are two essential components in conversational systems. Human-human dialogues are not well-controlled and often random and unpredictable due to their own goals and speaking habits.…

Computation and Language · Computer Science 2017-10-03 Ta-Chung Chi , Po-Chun Chen , Shang-Yu Su , Yun-Nung Chen

Extended reasoning models represent a transformative shift in Large Language Model (LLM) capabilities by enabling explicit test-time computation for complex problem solving. However, the optimal configuration of sampling temperature and…

Computation and Language · Computer Science 2026-04-13 Mousa Salah , Amgad Muneer