English
Related papers

Related papers: How do decoding algorithms distribute information …

200 papers

The Uniform Information Density (UID) hypothesis posits that speakers tend to distribute information evenly across linguistic units to achieve efficient communication. Of course, information rate in texts and discourses is not perfectly…

Computation and Language · Computer Science 2024-10-22 Eleftheria Tsipidi , Franz Nowak , Ryan Cotterell , Ethan Wilcox , Mario Giulianelli , Alex Warstadt

The uniform information density (UID) hypothesis posits a preference among language users for utterances structured such that information is distributed uniformly across a signal. While its implications on language production have been well…

Computation and Language · Computer Science 2021-09-27 Clara Meister , Tiago Pimentel , Patrick Haller , Lena Jäger , Ryan Cotterell , Roger Levy

Large language models (LLMs) often solve problems using step-by-step Chain-of-Thought (CoT) reasoning, yet these intermediate steps are frequently unfaithful or hard to interpret. Inspired by the Uniform Information Density (UID) hypothesis…

Computation and Language · Computer Science 2025-10-21 Minju Gwak , Guijin Son , Jaehyung Kim

The uniform information density (UID) hypothesis states that humans tend to distribute information roughly evenly across an utterance or discourse. Early evidence in support of the UID hypothesis came from Genzel & Charniak (2002), which…

Computation and Language · Computer Science 2023-10-19 Vivek Verma , Nicholas Tomlin , Dan Klein

The Uniform Information Density (UID) hypothesis posits that speakers are subject to a communicative pressure to distribute information evenly within utterances, minimising surprisal variance. While this hypothesis has been tested…

Computation and Language · Computer Science 2026-02-17 Matteo Gay , Coleman Haley , Mario Giulianelli , Edoardo Ponti

The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In this work, we revisit this principle in the context of Large Language Model (LLM) reasoning,…

Artificial Intelligence · Computer Science 2026-04-20 Minju Gwak , Guijin Son , Jaehyung Kim

The Uniform Information Density (UID) principle posits that humans prefer to spread information evenly during language production. We examine if this UID principle can help capture differences between Large Language Models (LLMs)-generated…

Computation and Language · Computer Science 2024-04-05 Saranya Venkatraman , Adaku Uchendu , Dongwon Lee

The ingrained principles of fairness in a dialogue system's decision-making process and generated responses are crucial for user engagement, satisfaction, and task achievement. Absence of equitable and inclusive principles can hinder the…

Computation and Language · Computer Science 2023-07-11 Anthony Sicilia , Malihe Alikhani

The uniform information density (UID) hypothesis proposes that speakers aim to distribute information evenly throughout a text, balancing production effort and listener comprehension difficulty. However, language typically does not maintain…

Computation and Language · Computer Science 2025-06-05 Eleftheria Tsipidi , Samuel Kiegeland , Franz Nowak , Tianyang Xu , Ethan Wilcox , Alex Warstadt , Ryan Cotterell , Mario Giulianelli

The uniform information density (UID) hypothesis, which posits that speakers behaving optimally tend to distribute information uniformly across a linguistic signal, has gained traction in psycholinguistics as an explanation for certain…

Computation and Language · Computer Science 2021-06-11 Jason Wei , Clara Meister , Ryan Cotterell

For open-ended language generation tasks such as storytelling and dialogue, choosing the right decoding algorithm is critical to controlling the tradeoff between generation quality and diversity. However, there presently exists no consensus…

Computation and Language · Computer Science 2020-04-23 Hugh Zhang , Daniel Duckworth , Daphne Ippolito , Arvind Neelakantan

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…

Computation and Language · Computer Science 2018-09-06 Ashutosh Baheti , Alan Ritter , Jiwei Li , Bill Dolan

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…

Computation and Language · Computer Science 2022-10-17 Anthony Sicilia , Malihe Alikhani

When generating natural language from neural probabilistic models, high probability does not always coincide with high quality: It has often been observed that mode-seeking decoding methods, i.e., those that produce high-probability text…

Computation and Language · Computer Science 2022-04-01 Clara Meister , Gian Wiher , Tiago Pimentel , Ryan Cotterell

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the…

Computation and Language · Computer Science 2021-06-08 Wei Wei , Jiayi Liu , Xianling Mao , Guibing Guo , Feida Zhu , Pan Zhou , Yuchong Hu

Despite the recent advances in open-domain dialogue systems, building a reliable evaluation metric is still a challenging problem. Recent studies proposed learnable metrics based on classification models trained to distinguish the correct…

Computation and Language · Computer Science 2023-05-26 ChaeHun Park , Seungil Chad Lee , Daniel Rim , Jaegul Choo

Despite considerable advancements with deep neural language models, the enigma of neural text degeneration persists when these models are tested as text generators. The counter-intuitive empirical observation is that even though the use of…

Computation and Language · Computer Science 2020-02-18 Ari Holtzman , Jan Buys , Li Du , Maxwell Forbes , Yejin Choi

Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natural language…

Artificial Intelligence · Computer Science 2021-03-23 Haoyu Song , Wei-Nan Zhang , Jingwen Hu , Ting Liu

In open-ended natural-language generation, existing text decoding methods typically struggle to produce text which is both diverse and high-quality. Greedy and beam search are known to suffer from text degeneration and linguistic diversity…

Computation and Language · Computer Science 2022-11-15 Mirac Suzgun , Luke Melas-Kyriazi , Dan Jurafsky

Intelligent dialogue systems are expected as a new interface between humans and machines. Such an intelligent dialogue system should estimate the user's internal state (UIS) in dialogues and change its response appropriately according to…

Computation and Language · Computer Science 2020-12-08 Takashi Kodama , Ribeka Tanaka , Sadao Kurohashi
‹ Prev 1 2 3 10 Next ›