arXiv:2604.01413v1 Announce Type: new
Abstract: Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These …
arXiv:2604.01993v1 Announce Type: new
Abstract: Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynam…
arXiv:2604.02145v1 Announce Type: cross
Abstract: AI models of equivalent capability can exhibit fundamentally different behavioral patterns, yet no standardized instrument exists to measure these dispositional differences. Existing approaches either …
arXiv:2604.02043v1 Announce Type: new
Abstract: Self-supervised speech models learn effective representations of spoken language, which have been shown to reflect various aspects of linguistic structure. But when does such structure emerge in model tr…
arXiv:2510.21884v2 Announce Type: replace
Abstract: Large Language Models (LLMs) increasingly produce natural language explanations alongside their predictions, yet it remains unclear whether these explanations reference predictive cues present in the…
arXiv:2604.02045v1 Announce Type: new
Abstract: Transforming causal generative language models into bidirectional encoders offers a powerful alternative to BERT-style architectures. However, current approaches remain limited: they lack consensus on op…
arXiv:2604.01467v1 Announce Type: new
Abstract: Persian poetry is often remembered through recurrent symbols before it is remembered through plot. Wine vessels, gardens, flames, sacred titles, bodily beauty, and courtly names return across centuries, …
arXiv:2604.02047v1 Announce Type: new
Abstract: Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept …
arXiv:2604.01504v1 Announce Type: new
Abstract: Research on Large Language Models (LLMs) studies output variation across generation, reasoning, alignment, and representational analysis, often under the umbrella of “diversity.” Yet the terminology rema…
arXiv:2604.02091v1 Announce Type: new
Abstract: Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated relevance labels in iso…