Learning to Decode for Future Success
read the original abstract
We introduce a simple, general strategy to manipulate the behavior of a neural decoder that enables it to generate outputs that have specific properties of interest (e.g., sequences of a pre-specified length). The model can be thought of as a simple version of the actor-critic model that uses an interpolation of the actor (the MLE-based token generation policy) and the critic (a value function that estimates the future values of the desired property) for decision making. We demonstrate that the approach is able to incorporate a variety of properties that cannot be handled by standard neural sequence decoders, such as sequence length and backward probability (probability of sources given targets), in addition to yielding consistent improvements in abstractive summarization and machine translation when the property to be optimized is BLEU or ROUGE scores.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-wor...
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.