3 citations · 7 across the 6 of their papers we have counts for
8 papers · 1 filter
Tracing How Language Models Integrate Temporal Anchors into Factual Recall
Ayana Niwa, Masahiro Kaneko, Kentaro Inui
Factual recall in language models is typically framed as retrieving a factual association: a subject--relation pair maps to a single object. However, many facts are context-depende…
Rethinking the Evaluation of LLM Fact-Checkers
Ayana Niwa, Miyu Yamada, Kouta Nakayama +3
Large language models (LLMs) are widely used to answer factual questions, but their answers can contain errors and must be fact-checked claim by claim. Yet the resulting score depe…
JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs
Taihei Shiotani, Masahiro Kaneko, Ayana Niwa +4
Social biases reflected in language are inherently shaped by cultural norms, which vary significantly across regions and lead to diverse manifestations of stereotypes. Existing eva…
Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning
Ayana Niwa, Masahiro Kaneko, Kentaro Inui
Large language models (LLMs) can exhibit advanced reasoning yet still generate incorrect answers. We hypothesize that such errors frequently stem from spurious beliefs, proposition…
ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
Ryuto Koike, Masahiro Kaneko, Ayana Niwa +2
Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions, such as undermining students' academic dignity. LLM text detection…
AmbigNLG: Addressing Task Ambiguity in Instruction for NLG
Ayana Niwa, Hayate Iso
We introduce AmbigNLG, a novel task designed to tackle the challenge of task ambiguity in instructions for Natural Language Generation (NLG). Ambiguous instructions often impede th…
Nearest Neighbor Non-autoregressive Text Generation
Ayana Niwa, Sho Takase, Naoaki Okazaki
Non-autoregressive (NAR) models can generate sentences with less computation than autoregressive models but sacrifice generation quality. Previous studies addressed this issue thro…
Interpretability for Language Learners Using Example-Based Grammatical Error Correction
Masahiro Kaneko, Sho Takase, Ayana Niwa +1
Grammatical Error Correction (GEC) should not focus only on high accuracy of corrections but also on interpretability for language learning. However, existing neural-based GEC mode…