Another 215papers do not have category tags yet and are not included in filtered results.
Proposes RATED, which reranks agent tool retrieval using execution feedback
Proposes SAFE-QE, which filters unsupported hallucinated words in LLM query expansion
AbstractSAFE-QE suppresses expansion hallucinations with reproducibility and coverage selection; the authors say ranking quality shows no visible cost.
Propose KVeil, which adds perturbations to face videos to prevent unauthorized customization from reproducing identity
AbstractKVeil adapts LETHE's reference-reading disruption to the challenge's two stages, ranking first on the leaderboard in both Final columns.
Proposes SWE-DeceptionBench to evaluate LLM deception in the software development lifecycle
Proposes LETHE, which perturbs reference images to block unauthorized image-to-video
LETHE is a protective perturbation added to personal images before publication, used to counter unauthorized image-to-video generation.
Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel
The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.
Auditing training labels for label-only backdoors, comparing spaces and statistics, and judging by retraining
The authors ask: can a defender without trusted data decide which training labels to keep, and how much clean data this destroys, and what the final model accuracy is.
Introduces DistressBench, evaluating models' multidimensional support in crisis conversations
DistressBench uses SSH dialogues written and revised by clinical personnel, and evaluates how much necessary care general chat models deliver according to weighted atomic criteria, rather than whether they refuse. When users disclose suicidal ideation or self-harm to a chat model, the authors consider the expected behavior to be recognizing the crisis, calibrating empathy, de-escalating, and referring to human help. Refusal-based evaluations cannot detect failing to act after recognizing the crisis.
Measuring the impact of random weight bit flips on LLM agent safety and alignment behavior
After random two-bit weight faults enter an LLM agent, model-level damage becomes recoverable, increased cost, subtle semantic errors, and changes in safety or alignment behavior.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
Proposes Task Bank self-replay to mitigate held-out forgetting in continual instruction tuning
The authors study how language models, when learning new tasks, can use their own knowledge for broader self-preservation: given an incomplete list and forgetting that extends beyond the list, can the model generate replay and help choose targets.
Proposes the ISE framework to evaluate the epistemic humility of LLM agents under knowledge conflicts
What the authors want to test is not whether the agent's final answer is correct, but whether, when a knowledge conflict arises, it recognizes the gap in its trajectory, performs bounded tool follow-up, and writes the unresolved uncertainty to the user.
Diagnose whether compliance system rulings change with perturbations to regulatory rules
Use behavioral counterfactuals and activation probes to audit whether compliance rulings rely on the given rules. The authors aim to separate two kinds of seemingly identical correct rulings: those that use the given rules, and those obtained from case surface features or training patterns.
Proposes ReSI, which recursively improves model safety alignment using automatic red teaming and recipe search.
Analyzing why optimizing teaching adaptation metrics collapses tutoring choices and diverges from expert judgment
After turning teaching adaptation metrics into a fine-tuning objective, the metrics rise while scores from trained educators decline.
Using fear activation steering to test the hazard judgment criteria of vision-language models
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.
提出 IRIS，用意图恢复率区分遮蔽越狱下无害输出的原因
IRIS 把意图恢复当作中间信号，用来解释意图遮蔽提示下为何没有出现有害协助。
评测编码 Agent 中相似技能共同安装对已装技能核心功能的替代
作者对共同安装、做同一件事的良性 skill 做实证研究，用核心功能是否还在，而不是任务过不过，来看冲突。。