Pith. sign in

REVIEW 3 cited by

Shaking the foundations: delusions in sequence models for interaction and control

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 2110.10819 v1 pith:7I33JNVF submitted 2021-10-20 cs.LG cs.AI

classification cs.LGcs.AI
keywords modelssequenceactionsdelusionslearningadaptiveappliedauto-suggestive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains. One important problem class that has remained relatively elusive however is purposeful adaptive behavior. Currently there is a common perception that sequence models "lack the understanding of the cause and effect of their actions" leading them to draw incorrect inferences due to auto-suggestive delusions. In this report we explain where this mismatch originates, and show that it can be resolved by treating actions as causal interventions. Finally, we show that in supervised learning, one can teach a system to condition or intervene on data by training with factual and counterfactual error signals respectively.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 7 citations worldwide. Full citation record

  1. Safety from Honesty in a Disinterested AI Predictor

    cs.AI 2026-06 unverdicted novelty 7.0 of 10

    Under consequence-invariant posterior training and sparsity of coordinated harm patterns, the training mass on dangerous guarded Predictors is bounded by C_bad times R_shell.

  2. Scalable Causal Imitation Learning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Causal SQIL and Causal IQ-Learn combine sliding-window causal adjustment with off-policy soft Q-learning, scaling causal imitation learning to long-horizon continuous control.

  3. Reinforcement Learning: From Algorithms To Foundation Models

    cs.AI 2026-07 conditional novelty 3.0 of 10

    A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.

Pith tools