arXiv:2602. 07356v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands.
arXiv:2609.39701v1 Announce Type: new Abstract: Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Convention...
arXiv:2602. 03160v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles.
The paper introduces Training-Free Task Vectors (TFTVs), a method for computing task-vector-like directions in large language models without fine‑tuning. TFTVs map activation steering vectors to rank‑one weight‑space edits using only forward‑pass statistics, enabling arithmetic operations such as learning, forgetting, and composing edits. Experiments show that TFTVs consistently amplify, suppress, and combine target behaviors while preserving general knowledge, outperforming other editing and steering baselines.
The paper introduces AIMES, a framework for adaptive multi-value activation steering in large language models. AIMES builds layer‑specific bipolar directions for moral‑foundation values and uses intermediate‑layer vocabulary readouts as online observers to guide a controller that adjusts intervention strengths at each decoding step. Experiments across instruction‑tuned model families show that AIMES achieves depth‑dependent advantages over fixed joint steering and prompt‑based steering, with smaller activation‑space interventions and comparable response quality.
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
arXiv:2510. 26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems.
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
arXiv:2503. 02368v4 Announce Type: replace-cross Abstract: While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs without re-training models, its effectiveness is limited by the accuracy of the value function.
arXiv:2601.12758v2 Announce Type: replace-cross Abstract: As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preferen...
arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especiall...
arXiv:2606. 11206v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization.
arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing...