Pith. sign in

REVIEW 6 cited by

Unintentional Unalignment: Likelihood Displacement in Direct 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

arxiv 2410.08847 v4 pith:IXR4SN42 submitted 2024-10-11 cs.LG cs.AIcs.CLstat.ML

classification cs.LGcs.AIcs.CLstat.ML
keywords responsesdisplacementlikelihoodpreferredchesmodelpreferencesprobability
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a model to generate preferred responses more frequently relative to dispreferred responses, prior work has observed that the likelihood of preferred responses often decreases during training. The current work sheds light on the causes and implications of this counter-intuitive phenomenon, which we term likelihood displacement. We demonstrate that likelihood displacement can be catastrophic, shifting probability mass from preferred responses to responses with an opposite meaning. As a simple example, training a model to prefer $\texttt{No}$ over $\texttt{Never}$ can sharply increase the probability of $\texttt{Yes}$. Moreover, when aligning the model to refuse unsafe prompts, we show that such displacement can unintentionally lead to unalignment, by shifting probability mass from preferred refusal responses to harmful responses (e.g., reducing the refusal rate of Llama-3-8B-Instruct from 74.4% to 33.4%). We theoretically characterize that likelihood displacement is driven by preferences that induce similar embeddings, as measured by a centered hidden embedding similarity (CHES) score. Empirically, the CHES score enables identifying which training samples contribute most to likelihood displacement in a given dataset. Filtering out these samples effectively mitigated unintentional unalignment in our experiments. More broadly, our results highlight the importance of curating data with sufficiently distinct preferences, for which we believe the CHES score may prove valuable.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

    cs.CL 2026-06 conditional novelty 7.0 of 10

    Shared chat-template tokens piggyback narrow finetuning behaviors onto out-of-domain queries; regularizing their KV states (TReFT) reduces emergent misalignment and other off-topic generalization.

  2. The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    The cancellation hypothesis shows how rollout-level rewards produce token-level credit assignment in critic-free RL through cancellation of opposing signals on shared tokens, with empirical support and batching interv...

  3. The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    The Piggyback Hypothesis attributes emergent misalignment to chat-template tokens piggybacking finetuned behavior; Token-Regularized Finetuning (TReFT) mitigates it by regularizing prefix token representations.

  4. Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet

    cs.CL 2026-07 conditional novelty 5.0 of 10

    In medication-leaflet generation, ORPO and GRPO beat SFT and a zero-shot GPT-5 baseline, but GRPO's cross-domain advantage is partly built into its reward functions.

  5. Normalized Rewards for Preference Optimization

    cs.LG 2026-06 conditional novelty 5.0 of 10

    A regularization term that conserves the combined length-normalized probability of chosen and rejected responses reduces likelihood displacement in DPO/SimPO, improves AlpacaEval and benchmark outcomes, and acts prima...

  6. Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation

    q-bio.BM 2026-05 unverdicted novelty 4.0 of 10

    Moirain models use multimodal SFT and DPO to generate novel RNA sequences with superior protein binding affinities in a zero-shot conditional setting.

Pith tools