Pith. sign in

REVIEW 9 cited by

Out-of-Distribution Detection and Selective Generation for Conditional Language Models

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 2209.15558 v2 pith:T5OKJ53A submitted 2022-09-30 cs.CL

classification cs.CL
keywords languagemodelsselectiveclassificationclmsconditionaldetectiongenerated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Machine learning algorithms typically assume independent and identically distributed samples in training and at test time. Much work has shown that high-performing ML classifiers can degrade significantly and provide overly-confident, wrong classification predictions, particularly for out-of-distribution (OOD) inputs. Conditional language models (CLMs) are predominantly trained to classify the next token in an output sequence, and may suffer even worse degradation on OOD inputs as the prediction is done auto-regressively over many steps. Furthermore, the space of potential low-quality outputs is larger as arbitrary text can be generated and it is important to know when to trust the generated output. We present a highly accurate and lightweight OOD detection method for CLMs, and demonstrate its effectiveness on abstractive summarization and translation. We also show how our method can be used under the common and realistic setting of distribution shift for selective generation (analogous to selective prediction for classification) of high-quality outputs, while automatically abstaining from low-quality ones, enabling safer deployment of generative language models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios

    cs.CL 2026-06 unverdicted novelty 7.0 of 10

    OpenHalDet creates a standardized benchmark and open codebase for comparing hallucination detectors across diverse LLM generation scenarios and access settings.

  2. From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums

    cs.AI 2026-02 unverdicted novelty 7.0 of 10

    A new sequential interaction framework lets LLMs propose questions to forums, with simulations on real Stack Exchange data showing players can reach roughly half the utility of an ideal full-information scenario despi...

  3. TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    TriLens detects hallucinations via per-layer entropy trajectories of logit-lens readouts from three internal modules across LLMs and QA benchmarks.

  4. Entropy Distribution as a Fingerprint for Hallucinations in Generative Models

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    Token entropy distributions fingerprint hallucinations in generative models, enabling the Calibrated Entropy Score (CES) for single-pass black-box detection with calibration guarantees via a novel DKW inequality.

  5. Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.

  6. Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection

    cs.CL 2025-08 conditional novelty 6.0 of 10

    A decoding pipeline reuses cached tokens and anneals sampling temperature to accelerate self-consistency hallucination detection by up to 3x without meaningful AUROC loss.

  7. Learning Uncertainty from Sequential Internal Dispersion in Large Language Models

    cs.CL 2026-04 unverdicted novelty 5.0 of 10

    SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.

  8. Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Cleanse detects hallucinated LLM answers by computing the share of hidden-embedding cosine similarity that falls inside semantic clusters, and it beats several baselines in AUROC across four models and two QA benchmarks.

  9. Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection

    cs.CL 2025-09 reject novelty 4.0 of 10

    Singular values of label-grouped n-gram frequency tensors are used as MLP features for hallucination detection, with reported gains on HaluEval that rely on label-aware grouping.

Pith tools