arXiv:2606. 10298v1 Announce Type: new Abstract: When large language models generate from retrieved or augmented contexts, conflicts between external context and parametric priors remain a central reliability bottleneck.
arXiv:2606. 05644v1 Announce Type: new Abstract: When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of retrieval augmentation.
arXiv:2605.09492v3 Announce Type: replace Abstract: Reliable text generation is critical for deploying large language models (LLMs) in real-world applications, particularly in high-stakes domains suc...
arXiv:2602.00377v3 Announce Type: replace Abstract: Existing knowledge probing methods rely on pre-defined queries, limiting extraction to known concepts. We introduce DecompressionLM, a stateless fr...
arXiv:2608. 04509v1 Announce Type: new Abstract: Vision-language systems combine images with retrieved text, but these sources can disagree or jointly fail to support an answer.
arXiv:2609.00796v1 Announce Type: new Abstract: As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive a...
arXiv:2601.03199v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. Existing In-Context...
arXiv:2602.00612v3 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages d...
Long-context evaluations often test whether a model can recover distant evidence, but recoverability does not guarantee behavioral influence. We test the prediction that a distant discourse anchor can...
arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.
The paper introduces Variance‑Calibrated Modulation (VCM), a training‑free pre‑decoding technique that reshapes language model probability distributions before truncation. VCM uses two dynamic mechanisms: a Contextual Searchlight via PMI to suppress stopwords and highlight context‑relevant tokens, and an Adaptive Self‑Debiasing that applies scale‑invariant penalization based on real‑time logit standard deviation. Experiments on open‑ended generation, factual QA, and mathematical reasoning show that VCM consistently reduces the likelihood trap, improving diversity, coherence, and reasoning accuracy with minimal computational cost.
The paper introduces MWE‑ECL, a bilingual diagnostic framework that tests whether distant discourse anchors can override local lexical priors in multi‑word expression interpretation. It evaluates models on a 0‑128K context grid, finding that while retrieval of anchors is near perfect, the ability to change locally preferred readings varies, especially when the model’s default conflicts with the anchor. The study shows that explicit recoverability does not always translate into behavioral influence, with gaps differing across models and languages.
arXiv:2609.36828v1 Announce Type: new Abstract: Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences wi...