Consistency Training Can Entrench Misalignment
arXiv:2606.03810v2 Announce Type: replace-cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.…
by ODEFTO Group
arXiv:2606.03810v2 Announce Type: replace-cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.…
arXiv:2606.04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval…
arXiv:2606.05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user…
arXiv:2606.03938v2 Announce Type: replace-cross Abstract: Multi-epoch training is becoming the standard now that compute is growing faster than the supply…
Nature Machine Intelligence, Published online: 04 June 2026; doi:10.1038/s42256-026-01249-1 Yang et al. developed CrossDNA, a parameter-efficient language model for cross-strand…
arXiv:2606.01802v2 Announce Type: replace-cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio…
arXiv:2606.03489v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle…
arXiv:2606.03504v1 Announce Type: cross Abstract: We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language…