arXiv:2606. 07555v5 Announce Type: replace-cross Abstract: Local definitions can assign a familiar word a temporary meaning while its usual associations remain useful elsewhere.
arXiv:2606. 07555v1 Announce Type: cross Abstract: Glossaries, technical specifications, and system prompts routinely ask language models to use familiar words in unfamiliar ways.
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...
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:2603. 00270v3 Announce Type: replace-cross Abstract: Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood.
The paper investigates why Word-in-Context (WiC) remains difficult for language models, suggesting that the lack of an explicit sense inventory contributes to the challenge. By evaluating open LLMs on both WiC and traditional Word Sense Disambiguation (WSD) tasks, the authors find that providing candidate senses—akin to WSD—consistently improves WiC performance. Human evaluation indicates that many WiC errors stem from label ambiguity or mismatched sense boundaries, with models often over‑discriminating senses and making overly fine‑grained distinctions.
The paper investigates how large language models handle domain-specific jargon, comparing a general-purpose Llama‑3.1 with a version fine‑tuned on medical data. Two new medical jargon benchmarks reveal that the general model actually outperforms the fine‑tuned variant, and interpretability tools show the fine‑tuned model over‑emphasizes a few components linked to jargon predictions. Reweighting these components narrows the performance gap, and some jargon‑sensitive components also aid materials‑science tasks, indicating a partially domain‑agnostic representation of specialized terminology.
arXiv:2608. 03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant information is preserved.
arXiv:2606. 11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution.
The paper introduces ADU, a fine‑grained training framework that unlearns sensitive information from large language models by decoupling contextual attention pathways instead of erasing tokens. ADU exploits the distinction between local and global attention heads to identify and suppress attention paths that retrieve persistent sensitive anchors, while preserving local‑attention structure and overall language modeling performance. Evaluation on the TOFU and WMDP benchmarks shows ADU achieves superior forget quality (0.93 on TOFU) and retains 92.9% of model utility compared to 81.9% for existing baselines, with fewer side effects in benign contexts.
arXiv:2608. 14681v1 Announce Type: cross Abstract: Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeated words afresh, and whether post-training changes this default behavior.
arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.
arXiv:2609.39701v1 Announce Type: new Abstract: Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Convention...