REVIEW 5 cited by
Diverse Preference Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is particularly a problem for creative generative tasks where varied responses are desired. In this work we introduce Diverse Preference Optimization (DivPO), an optimization method which learns to generate much more diverse responses than standard pipelines, while maintaining the quality of the generations. In DivPO, preference pairs are selected by first considering a pool of responses, and a measure of diversity among them, and selecting chosen examples as being more rare but high quality, while rejected examples are more common, but low quality. DivPO results in generating 45.6% more diverse persona attributes, and a 74.6% increase in story diversity, while maintaining similar win rates as standard baselines. On general instruction following, DivPO results in a 46.2% increase in diversity, and a 2.4% winrate improvement compared to DPO.
Forward citations
Cited by 5 Pith papers
-
More Is Not More: What Matters for Diversity in LLM Opinions?
Diversity in LLM opinions comes mostly from the first persona sentence and from combining different interaction architectures, not from richer personas, temperature, or diversity instructions.
-
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Representation-based elliptical bonuses improve inference-time and post-training pass@k for LLM reasoning, but the headline AIME result is tainted by validation/test overlap.
-
Outcome-based Exploration for LLM Reasoning
Outcome-based exploration bonuses (UCB-Con and Batch) improve pass@1 and pass@32 for LLM math reasoning while slowing diversity collapse, supported by a bandit model with a strong generalization assumption.
-
Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
Anchoring rejected responses to the initial model and choosing responses from a future model raises AlpacaEval 2.0 win rate from 19.69 to 29.44 for Llama3.1-8B.
-
Quality-constrained Entropy Maximization Policy Optimization for LLM Diversity
Quality-constrained entropy maximization yields simple DPO-like objectives that increase LLM output diversity while preserving or slightly improving quality, with theoretical guarantees under tuned temperature conditions.
Discussion (0). Continue with ORCID to comment.