Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Madureira, Brielen"'
Autor:
Beyer, Anne, Chalamalasetti, Kranti, Hakimov, Sherzod, Madureira, Brielen, Sadler, Philipp, Schlangen, David
It has been established in recent work that Large Language Models (LLMs) can be prompted to "self-play" conversational games that probe certain capabilities (general instruction following, strategic goal orientation, language understanding abilities)
Externí odkaz:
http://arxiv.org/abs/2405.20859
Autor:
Madureira, Brielen, Schlangen, David
Active participation in a conversation is key to building common ground, since understanding is jointly tailored by producers and recipients. Overhearers are deprived of the privilege of performing grounding acts and can only conjecture about intende
Externí odkaz:
http://arxiv.org/abs/2405.01139
Incremental models that process sentences one token at a time will sometimes encounter points where more than one interpretation is possible. Causal models are forced to output one interpretation and continue, whereas models that can revise may edit
Externí odkaz:
http://arxiv.org/abs/2402.13113
Autor:
Madureira, Brielen, Schlangen, David
Clarification requests are a mechanism to help solve communication problems, e.g. due to ambiguity or underspecification, in instruction-following interactions. Despite their importance, even skilful models struggle with producing or interpreting suc
Externí odkaz:
http://arxiv.org/abs/2401.17039
In NLP, incremental processors produce output in instalments, based on incoming prefixes of the linguistic input. Some tokens trigger revisions, causing edits to the output hypothesis, but little is known about why models revise when they revise. A p
Externí odkaz:
http://arxiv.org/abs/2310.18229
Incremental dialogue model components produce a sequence of output prefixes based on incoming input. Mistakes can occur due to local ambiguities or to wrong hypotheses, making the ability to revise past outputs a desirable property that can be govern
Externí odkaz:
http://arxiv.org/abs/2307.15508
Autor:
Madureira, Brielen, Schlangen, David
Instruction Clarification Requests are a mechanism to solve communication problems, which is very functional in instruction-following interactions. Recent work has argued that the CoDraw dataset is a valuable source of naturally occurring iCRs. Beyon
Externí odkaz:
http://arxiv.org/abs/2306.02377
Autor:
Chalamalasetti, Kranti, Götze, Jana, Hakimov, Sherzod, Madureira, Brielen, Sadler, Philipp, Schlangen, David
Recent work has proposed a methodology for the systematic evaluation of "Situated Language Understanding Agents"-agents that operate in rich linguistic and non-linguistic contexts-through testing them in carefully constructed interactive settings. Ot
Externí odkaz:
http://arxiv.org/abs/2305.13455
Language is by its very nature incremental in how it is produced and processed. This property can be exploited by NLP systems to produce fast responses, which has been shown to be beneficial for real-time interactive applications. Recent neural netwo
Externí odkaz:
http://arxiv.org/abs/2305.10845
Autor:
Madureira, Brielen, Schlangen, David
In visual instruction-following dialogue games, players can engage in repair mechanisms in face of an ambiguous or underspecified instruction that cannot be fully mapped to actions in the world. In this work, we annotate Instruction Clarification Req
Externí odkaz:
http://arxiv.org/abs/2302.14406