Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
arXiv preprint arXiv:2009.06367 , year =
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
HDMI is a new probe-free technique that steers LLM hidden states via margin objectives to achieve more reliable causal interventions than prior probe-based methods on standard benchmarks.
Prefix-tuning matches or exceeds fine-tuning on NLG tasks by optimizing a continuous prefix using 0.1% of parameters while keeping the LM frozen.
Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics correlating to LLM judges.
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
Formalizes the jailbreak oracle problem for LLMs and introduces Boa, a two-phase breadth-first then depth-first search system to solve it efficiently.
Introduces ETHICS benchmark showing current language models have promising but incomplete ability to predict basic human ethical judgments on text scenarios.
citing papers explorer
-
Decision Transformer: Reinforcement Learning via Sequence Modeling
Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
-
Inference Time Causal Probing in LLMs
HDMI is a new probe-free technique that steers LLM hidden states via margin objectives to achieve more reliable causal interventions than prior probe-based methods on standard benchmarks.
-
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Prefix-tuning matches or exceeds fine-tuning on NLG tasks by optimizing a continuous prefix using 0.1% of parameters while keeping the LM frozen.
-
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics correlating to LLM judges.
-
Conditional Attribute Estimation with Autoregressive Sequence Models
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
-
Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
Formalizes the jailbreak oracle problem for LLMs and introduces Boa, a two-phase breadth-first then depth-first search system to solve it efficiently.
-
Aligning AI With Shared Human Values
Introduces ETHICS benchmark showing current language models have promising but incomplete ability to predict basic human ethical judgments on text scenarios.