September 11–17: 14 frontier papers out of 2,100 read.
Papers rated as moving the field
How we choose“We show that this can severely underestimate worst-case vulnerability: across three LLaMA-3-8B backdoor settings, holding the model, clean data, and poison count fixed, attack success ranges from 3% to 80% depending only on which poison set is chosen.”
The authors, in the abstract
Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
“For CBRN, we measure uplift across eight steps of a hypothetical bioweapon attack chain and find that consultation raises Gemma-4-31B's mean rubric score from 62.3 to 83.1 on a 100-point rubric scale.”
“On Long-Horizon Terminal Bench, T1 reaches 27.9% and surpasses GPT-5.4 and GLM-5.1.”
“Replaying identical factorial responses also yields a Claude headline mean 12.5 percentage points below Astra's, demonstrating evaluator sensitivity separately from target behavior.”
“Evaluation of 18 LLMs shows hallucination rates ranging from 0% to 39% across dimensions, and among non-hallucinated correct-positive judgments, over 70% cite evidence fails to logically support the stated reason.”
“For faster inference, our variant TabPFN-3.5-Fast runs up to 3x faster than TabPFN-3 while keeping most of the accuracy gains.”
“We show that DoM vectors are similarly effective but virtually free, catching 3.1% more hacks in Kimi K3 and 7.9% fewer hacks in GLM 5.2 on DeepSWE at a monitor matched false positive rate.”
“We had registered a prediction for that 58% before the run: 35%.”
“We also show that our pre-training design offers a 4.2x efficiency improvement in 16K pre-training time-to-loss.”
“Finally, we find cases where extra monitor resources cause harm - giving the monitor access to the injected plan drops detection by as much as 50% in the Bio-Math task and in a case study on monitor reasoning budget, we find transcripts where additional thinking tokens are spent rationalizing the injected plan rather than flagging it.”
“Experiments with existing reviewer models show that collective review can remain sound without an aligned individual, even when some disapprovals are tolerated.”
Sep 11–17: 208 cleared, 14 frontier
The week’s papers have not been sorted into fields yet.
194 papers