arXiv:2508.15754v2 Announce Type: replace-cross
Abstract: Tool use is often assumed to monotonically improve reasoning, where external evidence is expected to help when relevant and be ignored when i...
By Yufeng Zhao, Junnan Liu, Hongwei Liu, Dongsheng Zhu, Yuan Shen, Songyang Zhang, Kai Chen
The paper investigates how visual interventions—training‑free edits applied to multimodal large language models—affect hallucinations and prediction quality. By applying a visual‑residual edit across successive decoder layers and matching its RMS strength, the authors identify an Evidence Anchoring Boundary (EAB) where the intervention’s influence drops sharply; effects before the EAB are 13.78–26.10× larger than after it. They further compare counterfactual subtraction across different question types and introduce calibrated selective routing, which only alters predictions when calibration supports an intervention, improving attribute accuracy by 1.56–1.81 percentage points while avoiding the harms of universal subtraction.
By Qiji Zhou, Junyi Hu, Peiyu Wang, Yue Zhang
arXiv:2609.37616v1 Announce Type: new
Abstract: Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on th...
By Abhinav Rajeev Kumar (Lossfunk), Paras Chopra (Lossfunk)
The paper investigates how to efficiently repair stale key-value (KV) caches in retrieval‑augmented generation systems after document edits. It proposes a budgeted in‑place recomputation approach and evaluates training‑free position‑selection policies on a factual RAG benchmark. Across three model families, a contiguous edit‑local window consistently recovers most of the post‑edit answer quality while being 13–21 times faster than a full re‑prefill, though its effectiveness diminishes when answer‑bearing text moves downstream.
By Mingyang Mao, Wyatt Mackey, Xiaomin Lin
The paper introduces Verbalization Training (VT), a technique that encourages large language models (LLMs) to openly express their evaluation awareness (EA) without directly supervising their internal beliefs. VT works by truncating model rollouts just before spontaneous verbalizations, creating training prefixes that signal awareness, and then applying a reinforcement learning objective to increase calibrated verbalization. Experiments on models such as Qwen3.6-35B-A3B, Kimi K2.6, and Inkling show that VT boosts verbalized EA by 2.4–2.9× while keeping latent EA and overall behavior largely unchanged, and a causal study confirms that VT-induced verbalizations reflect newly acquired meta‑knowledge.
By Usman Anwar, Sahar Abdelnabi, David Krueger
The paper introduces Boundary‑Calibrated Intervention Transfer (BCIT), a method for conditional experience transfer in autonomous large language model (LLM) post‑training. BCIT links each past update to its specific parent model, data, and training stage, checks whether those conditions still hold, vetoes updates with hard conflicts, and, when necessary, runs a bounded training trial to confirm applicability before adopting the update. Experiments on a 4B model across finance reasoning, text‑to‑SQL, and function calling show that BCIT reduces harmful updates and achieves higher final‑model quality under equal computational budgets compared to other approaches.
By Tingyun Li, Wenfeng Feng, Weiqing Li, Abudukelimu Wuerkaixi, Guohua Liu, Yuewei Zhang