arXiv Machine Learning
Aug 11
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
arXiv:2605. 12705v2 Announce Type: replace Abstract: How can we train models whose post-trained capabilities survive subsequent fine-tuning?
Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
arXiv:2606. 30252v1 Announce Type: new Abstract: Inoculation prompting is a selective generalization technique used against Emergent Misalignment.
Related stories
arXiv Machine Learning
Aug 6
Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning
arXiv:2608. 04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence.
arXiv Machine Learning
Jun 11
Mechanisms of Introspective Awareness
arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.
arXiv AI
Aug 11
Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models
arXiv:2608. 08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per task.
arXiv AI
Aug 7
When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
arXiv:2608. 05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, newly added skills degrade performance instead of improving it.
Hugging Face Trending Papers
Aug 5
Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation process can also degrade alignment properties that were present in the source model.
arXiv AI
Jun 17
In-Context Environments Induce Evaluation-Awareness in Language Models
arXiv:2603. 03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}.
arXiv Computation and Language
Sep 16
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
arXiv:2604.15097v3 Announce Type: replace-cross Abstract: This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a...
arXiv AI
Jul 1
Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment
arXiv:2606. 31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts.
arXiv AI
Jun 24
Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
arXiv:2606. 23700v1 Announce Type: cross Abstract: Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content.
arXiv Computation and Language
Sep 7
EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?
EVOHARNESSBENCH is a new benchmark that tests how LLM-based agents handle changes in their tool, skill, and agent harnesses over time. It includes 17 deterministic harness streams with 802 tasks, 520 tools, 42 skills, and 62 agents, and evaluates agents in two settings: deployment evaluation and self‑evolving adaptation evaluation. The study finds that harness expansion can cause forgetting, adaptation gains are inconsistent, and preserving old competence does not always aid new capability adaptation, highlighting harness evolution as a distinct challenge for agent development.
arXiv AI
Aug 11
DarwinX: Evolving Agent Harnesses Through Natural Selection
arXiv:2608. 07545v1 Announce Type: cross Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow.