"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise

• URL: http://arxiv.org/abs/2606.01811v1
• Date: Mon, 01 Jun 2026 07:27:43 GMT
• Title: "I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise
• Abstract summary: We propose a new approach to measuring diversity using in-context learning.<n>A per-byte score read off the per-token log-probabilities of a base model.<n>On the OLMo-2-7B post-training pipeline, $D_Ca_n$ drops across the base $to$ SFT $to$ DPO $to$ RLVR stages, detecting the type of diversity loss that creative-writing applications care about.
• Score: 6.707563964399177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Measuring the diversity of creative outputs is central to evaluating post-training mode collapse, comparing decoding strategies, and quantifying creative behavior in both AI and human writing. We propose a new approach to measuring diversity using in-context learning, of which the ``Decan'' metric, $D_{Ca_n} = C \times a_n$, is the working instance we evaluate: a per-byte score read off the per-token log-probabilities of a base model $θ$ in a \emph{single forward pass} per permutation, with no embedding model, no reference corpus, and no human labels. This approach is grounded in information theory, makes use of language model in-context learning to detect a wide range of similarities between any number of inputs, and obviates the need to train a special-purpose model. The same pipeline scores AI samples and human-written response sets, with diversity treated as a property of (responses, prompt, scoring model). On Tevet and Berant's human-grounded McDiv benchmark, $D_{Ca_n}$ reaches OCA 0.846 on the McDiv prompt\_gen set where it performs best, behind the strongest neural baseline reported in Tevet and Berant (SentBERT, 0.897). On the OLMo-2-7B post-training pipeline, $D_{Ca_n}$ drops monotonically across the base $\to$ SFT $\to$ DPO $\to$ RLVR stages, detecting the type of diversity loss that creative-writing applications care about.

Related papers

• Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production [55.76222360698305]
  We explore a class of supervised training objectives that allow a language model to dynamically and autonomously scale the number of compute steps used for each input token.<n>For any token, the model can request additional compute steps by emitting a don't know> output.<n>We find that the CYB model requests additional steps when doing so improves accuracy, and the model adapts its processing time to token-level complexity and context.
  arXiv  Detail & Related papers  (2025-10-13T21:07:05Z)
• DISCO: Diversifying Sample Condensation for Efficient Model Evaluation [59.01400190971061]
  Costly evaluation reduces inclusivity, slows the cycle of innovation, and worsens environmental impact.<n>We argue that promoting diversity among samples is not essential; what matters is to select samples thatmaximise diversity in model responses.<n>Our method, $textbfDiversifying Sample Condensation (DISCO)$, selects the top-k samples with the greatest model disagreements.
  arXiv  Detail & Related papers  (2025-10-09T08:53:59Z)
• Reliability, Embeddedness, and Agency: A Utility-Driven Mathematical Framework for Agent-Centric AI Adoption [0.0]
  We formalize three axioms for sustained adoption of agent-centric AI systems executing multi-step tasks.<n>We model adoption as a sum of a decaying novelty term and a growing utility term.
  arXiv  Detail & Related papers  (2025-08-18T12:53:38Z)
• Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts [8.700087812420687]
  We provide guarantees for the model's performance on a different, unseen network "B"<n>We show how the principled vanilla DKW bound enables certification of the model's true performance on unseen clients within the same (source) network.
  arXiv  Detail & Related papers  (2024-10-26T18:45:15Z)
• Differentially Private Reward Estimation with Preference Feedback [15.943664678210146]
  Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. An adversarial attack in any step of the above pipeline might reveal private and sensitive information of human labelers. We focus on the problem of reward estimation from preference-based feedback while protecting privacy of each individual labelers.
  arXiv  Detail & Related papers  (2023-10-30T16:58:30Z)
• Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels [61.97359362447732]
  Learning from noisy labels is an important and long-standing problem in machine learning for real applications. In this paper, we reformulate the label-noise problem from a generative-model perspective. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets.
  arXiv  Detail & Related papers  (2023-05-31T03:01:36Z)
• Blessing of Class Diversity in Pre-training [54.335530406959435]
  We prove that when the classes of the pre-training task are sufficiently diverse, pre-training can significantly improve the sample efficiency of downstream tasks. Our proof relies on a vector-form Rademacher complexity chain rule for composite function classes and a modified self-concordance condition.
  arXiv  Detail & Related papers  (2022-09-07T20:10:12Z)
• Improving Robustness and Generality of NLP Models Using Disentangled Representations [62.08794500431367]
  Supervised neural networks first map an input $x$ to a single representation $z$, and then map $z$ to the output label $y$. We present methods to improve robustness and generality of NLP models from the standpoint of disentangled representation learning. We show that models trained with the proposed criteria provide better robustness and domain adaptation ability in a wide range of supervised learning tasks.
  arXiv  Detail & Related papers  (2020-09-21T02:48:46Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.