arXiv:2509. 24808v2 Announce Type: replace Abstract: Explaining why a language model produces a particular output requires local, input-level explanations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper investigates how increasing inference-time computation—via wider beam search or sample‑plus‑vote—affects performance on grammar‑constrained text‑to‑SQL tasks for small language models. Using the Qwen2.5‑Instruct family (0.5B–7B parameters) on the Spider benchmark, the authors find that larger models consistently outperform higher inference compute on the same model size, and that beam search yields better accuracy than sample‑plus‑vote under matched budgets. These results suggest that, unlike unconstrained settings, scaling inference compute does not compensate for smaller model size when strict grammar constraints are applied.
Large language models can solve complex multi‑hop tasks but often fail on simple two‑hop queries, even when each hop is individually correct. In a controlled symbolic setting, the authors find that models generalize reliably when the second hop follows the training distribution, but always fail when it deviates. Mechanistic analysis shows that successful generalization relies on consistent intermediate representations across contexts, whereas failures arise from a mismatch between lower‑layer representation construction and upper‑layer mapping to outputs. The study proposes a recurrent‑style training strategy that improves out‑of‑distribution two‑hop generalization.
CacheSpec is an inference optimization framework that transforms Program-of-Thoughts (PoT) style programs into reusable cache objects for large language models. By employing a small model for semantic variable extraction on cache hits and speculative drafting during target-LLM generation, CacheSpec reduces inference latency and improves cache reuse. Experiments on shopping, web, formula, and code QA datasets demonstrate up to 3.1× speedup in latency and 2.8× throughput gains over traditional PoT methods, while maintaining or improving task quality.
arXiv:2512. 20638v2 Announce Type: replace-cross Abstract: The evaluation of large language models relies heavily on standardized benchmarks.
arXiv:2602.21061v2 Announce Type: replace Abstract: Many current paths to more advanced AI depend on the assumption that large language models (LLMs) can generalize learned relationships to solve com...
arXiv:2607. 08399v1 Announce Type: cross Abstract: Large language models process prompts by propagating activations through dozens of layers before generating a response.