Pith. sign in

REVIEW 12 cited by

The pitfalls of next-token prediction

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 2403.06963 v3 pith:UR2GHQGH submitted 2024-03-11 cs.CL cs.AIcs.LG

The pitfalls of next-token prediction

classification cs.CL cs.AIcs.LG
keywords next-tokenfailpredictionpredictorteacher-forcingaccurateautoregressiveinference
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Can a mere next-token predictor faithfully model human intelligence? We crystallize this emerging concern and correct popular misconceptions surrounding it, and advocate a simple multi-token objective. As a starting point, we argue that the two often-conflated phases of next-token prediction -- autoregressive inference and teacher-forced training -- must be treated distinctly. The popular criticism that errors can compound during autoregressive inference, crucially assumes that teacher-forcing has learned an accurate next-token predictor. This assumption sidesteps a more deep-rooted problem we expose: in certain classes of tasks, teacher-forcing can simply fail to learn an accurate next-token predictor in the first place. We describe a general mechanism of how teacher-forcing can fail, and design a minimal planning task where both the Transformer and the Mamba architecture empirically fail in that manner -- remarkably, despite the task being straightforward to learn. Finally, we provide preliminary evidence that this failure can be resolved using _teacherless_ training, a simple modification using dummy tokens that predicts multiple tokens in advance. We hope this finding can ground future debates and inspire explorations beyond the next-token prediction paradigm. We make our code available under https://github.com/gregorbachmann/Next-Token-Failures

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

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

  1. Hierarchical Domain Generalization

    cs.LG 2026-07 conditional novelty 6.0

    Over infinite domains, hierarchy-uniform domain generalization is impossible for every nontrivial hypothesis class; a length-generalization bound is a property of the length hierarchy, not a hierarchy-free guarantee.

  2. FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts

    cs.AI 2026-06 conditional novelty 6.0

    FlowEdit fine-tunes LLMs so they enumerate all self-consistent answers to conflicting-condition problems, improving exact-set-match accuracy by 68% on a synthetic benchmark.

  3. DeepLook: Deeper Thinking with Lookahead

    cs.AI 2026-06 conditional novelty 6.0

    A training-free decoder that branches only at low-confidence reasoning segments and ranks continuations by average lookahead confidence reports equal or better accuracy at roughly 1/8 of a confidence-filtered baseline...

  4. Continuous Latent Diffusion Language Model

    cs.CL 2026-05 unverdicted novelty 6.0

    Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing l...

  5. Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation

    cs.IR 2026-04 unverdicted novelty 6.0

    STAMP mitigates semantic dilution in SID-based generative recommendation via adaptive input pruning and densified output supervision, delivering 1.23-1.38x speedup and 17-55% VRAM savings with maintained or improved accuracy.

  6. Multi-Token Prediction via Self-Distillation

    cs.CL 2026-02 unverdicted novelty 6.0

    Self-distillation turns pretrained autoregressive LMs into multi-token predictors that decode over 3x faster with under 5% accuracy drop on GSM8K.

  7. Representation Without Reward: A JEPA Audit for LLM Fine-Tuning

    cs.LG 2026-05 conditional novelty 5.0

    An empirical audit of 22 JEPA-style training auxiliaries on Llama-3.2-1B fine-tuning for regex generation finds no statistically significant task improvement after multiple-testing correction, even when auxiliaries vi...

  8. Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis

    cs.CR 2026-05 unverdicted novelty 5.0

    Pen-Strategist fine-tunes Qwen-3-14B with RL on a pentesting reasoning dataset and pairs it with a CNN step classifier, reporting 87% better strategy derivation, 47.5% more subtask completions than baselines, and gain...

  9. Noise is not always detrimental: the capacity of quantum batteries is enhanced in black holes

    quant-ph 2026-04 unverdicted novelty 5.0

    Hawking radiation is claimed to enhance quantum battery capacity for bipartite mixed states, while environmental noise generally degrades it in type-dependent ways.

  10. Noise is not always detrimental: the capacity of quantum batteries is enhanced in black holes

    quant-ph 2026-04 unverdicted novelty 5.0

    Hawking radiation enhances quantum battery capacity in black hole spacetimes, counter to typical noise effects, with degradation patterns depending on noise type.

  11. Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks

    cs.CL 2025-06 unverdicted novelty 5.0

    Direct Reasoning Optimization applies token-level Reasoning Reflection Reward (R3) focused on high-variance tokens and rubric-gating constraints to improve sample-efficient RL training of LLMs on unverifiable tasks.

  12. Retrieval-Augmented Generation with Graphs (GraphRAG)

    cs.IR 2024-12 unverdicted novelty 5.0

    A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.