A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models

GAPS: Dimension-Level Gates for Conditional Activation Steering

Activation steering suppresses undesired behaviors in language models by adding a steering vector to the hidden state during generation. Recent conditional methods such as CAST and DSAS improve the behavior-capability trade-off by deciding when to intervene, but once active, they apply the full dense vector to all hidden dimensions, regardless of whether a neuron carries concept information or already lies in the desired regime. We introduce dimension-level conditioning as a complementary axis of selectivity that also decides which neurons to intervene on. Our method, GAPS (Gated Activation steering via Posterior and Separability), combines two training-free gates: a static separability gate that restricts steering to neurons with statistically reliable concept information (via AUROC), and a dynamic posterior gate that steers a neuron only when its current activation is better explained by the undesired concept under a Gaussian model. The gates add O(D) overhead per token, and they plug into existing conditional methods. On toxicity mitigation (RealToxicityPrompts) and concept removal (OneSeC) with Gemma-3 (4B) and Qwen-3 (1.7B), GAPS consistently matches or improves the Pareto front of its token-level counterparts; under a fixed capability budget, DSAS+GAPS reduces Gemma-3's toxicity rate from 6.52% to 0.48%, versus 3.52% for DSAS alone. Ablations attribute most of the gain to the posterior gate.

Forecasting Side Effects of Activation Steering

Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retraining. While effective, steering often produces unintended side effects on other behaviors, making it difficult to deploy safely. We therefore ask: can these side effects be forecasted before steering is applied? We answer this question by constructing a cross-effect matrix over a taxonomy of 67 behaviors across three open-weight language models. We find that side effects are common, structured, and often asymmetric, revealing interactions that cannot be explained by existing similarity-based heuristics. Despite this complexity, we show that side effects are largely predictable before steering is performed. Their magnitude depends primarily on the target behavior, while their direction can be forecasted from the model's unsteered representations with substantially higher accuracy than simple baselines. Our results demonstrate that activation steering has systematic and forecastable side effects, enabling proactive safety auditing and more informed deployment of steering interventions.

Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias

This work develops a black-box method for learning a single context-independent logit-bias vector, added at every decoding step, without modifying model weights or requiring gradients, and suggests that learned logit bias is a lightweight mechanism for adapting language models under minimal access requirements.

XTC: Head-Aware Sampling by Excluding Top Choices

Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-probability tail. These strategies overlook a common regime of open-ended generation in which several continuations are plausible but too much probability mass remains concentrated on the most generic choice. We introduce XTC (Exclude Top Choices), a lightweight head-aware decoding operator that targets this regime directly. XTC identifies tokens whose probabilities exceed an absolute plausibility threshold $\tau$: when at least two qualify, it removes the dominant eligible choices with probability $\rho$ and retains only the weakest plausible alternative before renormalization. Across 60 experiments on Gemma 3 27B Q4, Gemma 3 12B Q6, and DeepSeek R1 14B Q6, with scaling validation on Llama 3.3 70B Q4, XTC improves the diversity-repetition Pareto frontier. On creative generation, Distinct-2 increases by 11--15% and repeat trigrams decrease by 27--47% across the four models. Combined with temperature scaling, gains reach 38% in Distinct-2 and 71% in repeat-trigram reduction over baseline. A blinded Amazon Mechanical Turk study with 150 Master raters yields a 62.3% creativity preference for XTC ($p<10^{-4}$) without reduced fluency, while a GPT-4o control judge reproduces the Anthropic-judge direction on every measure. On IFEval with Llama 3.3 70B Q4, XTC preserves prompt-level strict accuracy within 1.7 percentage points of baseline while recovering most of the diversity gain; a temperature setting matched on Distinct-2 reduces IFEval by 8.8 points. The effect is additive with temperature and repetition penalties, robust across quantization levels and model families, and consistent across twelve prompt genres. XTC has been adopted by llama.cpp, ExLlamaV2, and text-generation-webui.

Multi-Turn Reinforcement Learning for Large Language Models: From Theory to Practice with Amazon SageMaker AI

This hands-on problem-solving tutorial provides both a rigorous algorithmic and practical introduction to multi-turn RL finetuning for LLMs, and covers state-of-the-art multi-turn RL finetuning algorithms, turn-level vs. trajectory-level reward design, and production grade monitoring for reward hacking detection.