Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space
We introduce Output-Space Search (OS-Search), which turns LLM generation into endpoint search. An outer loop selects a target z* in a frozen encoder-defined 3D output space Z, and a retrieval-grounded policy trained with sequence-level RL generates outputs whose coordinates land near z* under standard autoregressive decoding. This enables parallel sweeps and black-box optimization in Z without path-dependent token/program search. On stories, sweeping Z (text) yields 3.1x higher LLM-scored diversity than prompt-chaining. On code, Bayesian optimization over Z (code) improves an objective withheld from the controller under matched inference budgets while preserving validity.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Beyond One Output: Visualizing and Comparing Distributions of Language Model Generations
Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as…
Parallel Decoder Transformer: Planner-Seeded Latent Coordination for Synchronized Parallel Decoding
Autoregressive language models can often identify parallel subproblems, but standard decoding exposes only a single left-to-right output interface. External orchestration methods can launch multiple prompts concurrently,…
Agreement in Representation Space for Open-Ended Self-Consistency
Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefore remain limited to tasks with categoric…
Mathematical ReasoningText SummarizationCode GenerationTask-Awareness Improves LLM Generations and Uncertainty
In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values, or graphs. Yet, existing decoding and uncertainty estimation methods ope…
TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models
Despite Multi-modal Large Language Models (MM-LLMs) have made exciting strides recently, they are still struggling to efficiently model the interactions among multi-modal inputs and the generation in non-textual modaliti…
All