arXiv AI
Jun 11
Forecasting Future Behavior as a Learning Task
arXiv:2606. 11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs.
Predicting Future Behaviors in Reasoning Models Enables Better Steering
arXiv:2606. 11172v1 Announce Type: new Abstract: Deployed large reasoning models (LRMs) often behave unexpectedly.
Related stories
arXiv AI
Jul 17
Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring
arXiv:2512. 14332v2 Announce Type: replace-cross Abstract: The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately.
arXiv Machine Learning
Jun 9
ATLAS: Verifier-Guided Adaptive Latent Activation Steering for Efficient LLM Reasoning
arXiv:2601. 03093v2 Announce Type: replace Abstract: Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without updating model parameters.
arXiv Machine Learning
Jun 16
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
arXiv:2601. 22642v2 Announce Type: replace Abstract: Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid.
arXiv AI
Jul 21
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
arXiv:2607. 18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable.
arXiv AI
Jul 24
Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv Machine Learning
Aug 11
Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond
arXiv:2510. 19990v2 Announce Type: replace Abstract: The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving.
arXiv AI
Jul 29
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
arXiv:2601. 03595v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (\eg backtracking, cross-verification) during the reasoning process, which improves their performance on complex tasks.
arXiv AI
Jun 2
Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners
arXiv:2606. 01810v1 Announce Type: new Abstract: Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning.
arXiv Machine Learning
Jun 11
When is Your LLM Steerable?
arXiv:2606. 11599v1 Announce Type: cross Abstract: Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration.
Hugging Face Trending Papers
Jun 10
When is Your LLM Steerable?
Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration. Finding the regime and boundaries of successful steering typically requires expensive grid searches and post-hoc evaluation of full autoregressive rollouts.
arXiv AI
Jun 3
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
arXiv:2602. 10352v2 Announce Type: replace-cross Abstract: Self-interpretation methods prompt language models to describe their own internal states, but remain unreliable due to hyperparameter sensitivity.