Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology. However, existing retrieval-augmented machine translation systems typically apply predefined retrieval strategies uniformly across all inputs. We argue t...
Shijun Li, Yang Liu, Najmeh Sadoughi et al.· 0 citations
Data augmentation (DA) plays a vital role in improving model performance in low-resource or limited-supervision scenarios within Natural Language Processing (NLP). Existing DA methods, such as synonym replacement and back-translation, have demonstrated effectiveness on the word or sentence level; however, they frequent...
Rui-Lin Shang, Shi-Long Hou, Zi Long et al.· 0 citations
Legal reasoning is a fundamental capability for large language models (LLMs) to complete legal AI tasks such as legal judgment prediction. In legal practice, this reasoning is shaped by legal philosophy: a judge's view of the nature and sources of law guides how legal materials are interpreted and applied, so judges wo...
Shuyuan Zheng, Yun-seo Lee, Xing Gao et al.· 0 citations
Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases--e.g., a"blind faith in text"--but why preferences vary across models, domains, and input conditions remains unclear. We develop a predictive account from a Bayesian perspec...
J. Barua, Kyle Mahowald, William Rudman· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Korean neologisms arise through diverse mechanisms, a demanding test of language models beyond lexical memorization. To enable systematic evaluation, we introduce NeoTrace, an automated, rerunnable framework that collects and dates neologisms across genres. Its 4,271 entries support KoAGE, a cutoff-aware benchmark with...
Massively multilingual speech modeling has made remarkable progress in recent years, yet existing training resources and benchmarks still underrepresent much of the linguistic long tail. To address this gap, we introduce ELARSpeech, a large-scale multilingual speech resource comprising 30,202 hours of speech across 675...
Sangmin Lee, Yejin Jeon, David Ifeoluwa Adelani· 0 citations
Does a language model answer better because its compressed memory contains useful document information? Replacing memory vectors with zeros can lower a trained model's score without showing that it outperforms a model trained without memory. We combine zeroing with separately trained models that cannot access stored te...
Minsu Oh, Seunghui Jwa, Chanjun Park et al.· 0 citations
Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions. A common approach to improving LLM agents is to use more capable expert models to provide training supervision, either by behavior cloning the expert'...
Thomas Zeng, Zelei Cheng, Mingyang Zhou et al.· 0 citations
This paper presents LLM-jp-4, a family of Japanese sovereign large language models (LLMs) developed with an emphasis on transparency, reproducibility, and practical usability. LLM-jp-4 comprises an 8B dense model and a 32B-A3B mixture-of-experts model, both trained from scratch on approximately 12 trillion tokens. To s...
Benchmarks shape how model capabilities are measured and interpreted, yet their scores can obscure whose conventions, contexts, and judgments define successful performance. We introduce a user-centric audit framework that distinguishes users who contribute benchmark content from those whose needs evaluation results are...
Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the ability of LLMs to copy in context can be improved through explicit modeling. We propose Copy-Paste Language Models (CPLMs), which add a lightweight Copy-Paste head to the conventional language modeling (LM)...
Transformer language models develop attention heads that specialize in syntactic relations, for example, attending from verbs to their subjects. Do these heads play a causal role in the model's syntactic predictions? Evidence for such a role is mixed to negative: even when we force these heads to attend to a distractor...
