arXiv:2606. 29604v1 Announce Type: cross Abstract: We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes.
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
arXiv:2511. 08577v3 Announce Type: replace-cross Abstract: Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications.
arXiv:2605. 00994v2 Announce Type: replace-cross Abstract: Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors.
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.
arXiv:2608. 06111v1 Announce Type: cross Abstract: Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to \textit{syntactic structure}.
arXiv:2607. 16204v1 Announce Type: new Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments.
arXiv:2512. 13374v2 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) open new perspectives for automation in optimization, yet little is known about whether their internal representations capture problem structure or algorithmic behavior.
arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.
arXiv:2605. 06890v3 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control.
arXiv:2606. 16244v1 Announce Type: cross Abstract: Large language models routinely generate code with exploitable security flaws.
arXiv:2606. 24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize.
arXiv:2607. 20520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures.