arXiv:2606. 02991v1 Announce Type: cross Abstract: We introduce TypewriterLM, a 7.
arXiv:2607. 11889v1 Announce Type: cross Abstract: Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences.
arXiv:2609.00082v1 Announce Type: cross Abstract: LLMs acquire vast amounts of knowledge during pre-training, but often lack the specialized knowledge needed to answer questions from niche sources su...
arXiv:2608. 25826v1 Announce Type: cross Abstract: A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rewriting the text itself, but it operates on short web passages, recovers only local thoughts, and leaves the structure of whole documents untouched.
arXiv:2601. 22146v2 Announce Type: replace-cross Abstract: Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data.
arXiv:2607. 17524v1 Announce Type: cross Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task.
The paper introduces the problem of cross‑lingual loopholes in large language model (LLM) unlearning, where forgetting a fact in one language can leave it accessible in others. It presents a new 174‑language benchmark, the Cross‑Lingual Unlearning Tensor, and proposes COVER, a method that selects a subset of source languages to maximize unlearning coverage under a language budget. Experiments show COVER reduces residual knowledge by 7.8–27.3% compared to uniform selection and works on both synthetic and real low‑resource news data.
A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rewriting the text itself, but it operates on short web passages, recovers only local thoughts, and leav...
The paper introduces a method for improving fine-grained, temporally aligned outputs in Speech Large Language Models (SpeechLLMs) by replacing absolute timestamps with relative timestamps, which reduces vocabulary size and enhances generalization. It proposes a hybrid fine‑tuning strategy that fully fine‑tunes the timestamp‑augmented embedding layer and language model head while applying LoRA to decoder layers, and introduces a masked timestamp training objective to prevent over‑reliance on ground‑truth timestamps. Experiments show significant gains in timestamp prediction accuracy without compromising transcription quality.
arXiv:2606. 26807v1 Announce Type: new Abstract: We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during token generation.
arXiv:2609.07798v1 Announce Type: cross Abstract: Natural Language Processing (NLP) in the climate domain requires models to process heterogeneous text sources, including scientific literature, polic...
arXiv:2609.23178v1 Announce Type: new Abstract: Language models are appealing tools for research on the past. But to trust the evidence a model provides, researchers need to know whether its response...
Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned outputs remains underexplored. Our work addresses t...