Producing natural and accurate responses like human beings is the ultimate goal of intelligent dialogue agents. So far, most of the past works concentrate on selecting or generating one pertinent and fluent response according to current query and its...
Evaluating the naturalness of dialogue in language models (LMs) is not trivial: notions of 'naturalness' vary, and scalable quantitative metrics remain limited. This study leverages the linguistic notion of 'at-issueness' to assess dialogue naturalne...
Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires evaluation met...
We present an empirical investigation of various ways to automatically identify phrases in a tagged corpus that are useful for dialogue act tagging. We found that a new method (which measures a phrase's deviation from an optimally-predictive phrase...
A growing body of work has shown that AI-assisted methods -- leveraging large language models, social choice methods, and collective dialogues -- can help navigate polarization and surface common ground in controlled lab settings. But what can these...
Feb 20, 2014 · I thought information is singular and plural. But now I'm not sure which version is right: The dialogue shows two important informations. OR The dialogue shows two important information. …
Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to compare and contrast them effectively. Motivated by this, we introduc...
We introduce Doctor XAvIer, a BERT-based diagnostic system that extracts relevant clinical data from transcribed patient-doctor dialogues and explains predictions using feature attribution methods. We present a novel performance plot and evaluation m...
Driven by the rapid advancement of Large Language Models (LLMs), particularly Audio-LLMs and Omni-models, spoken dialogue systems have evolved significantly, progressively narrowing the gap between human-machine and human-human interactions. Achievin...
Human–artificial intelligence (AI) dialogues can meaningfully impact voters’ attitudes towards presidential candidates and policy, demonstrating the potential of conversational AI to influence political decision-making.
Large Language Models (LLMs) are evolving beyond their classical role of providing information within dialogue systems to actively engaging with tools and performing actions on real-world applications and services. Today, humans verify the correctness and appr…
out the characters. During conversations with other characters, several choices of dialogue are presented. The currently selected choice is highlighted
Penelope descends, and receives the presents of the suitors. The dialogue of Ulysses with Eurymachus. While fix’d in thought the pensive hero sate, A mendicant approach’d the royal gate; A surly vagrant …
tear gas. President Nicolas Maduro said on his talk show that the MUD had ceased dialogue concerning the protests. President Maduro also made claims that
Nov 30, 2022 · We’ve trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, …
Nov 11, 2025 · The Arctic reflects today’s global challenges: peaceful and cooperative dialogue over conflict, sustainable development over exploitation, and shared responsibility over indifference or, …
Nov 28, 2025 · Research - Science - Diplomacy - Security - Education Videos of speeches and panels will be posted on the Arctic Circle YouTube Channel.
Jan 16, 2026 · The Strategic Intelligence platform uses a blend of human and machine intelligence that helps make sense of the interconnected world and enable informed, systemic and forward-looking …
Jan 16, 2026 · The Strategic Intelligence platform uses a blend of human and machine intelligence that helps make sense of the interconnected world and enable informed, systemic and forward-looking …
Community rules play a key part in enabling or constraining the behaviors of members in online communities. However, little is unknown regarding whether and to what degree changing rules actually affects community dynamics. In this paper, we seek to...