Pith. sign in

REVIEW 9 cited by

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 2411.04282 v2 pith:UL5VIBMO submitted 2024-11-06 cs.AI cs.CLcs.LGstat.ML

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding

classification cs.AI cs.CLcs.LGstat.ML
keywords reasoninglatrocapabilitieslatentmodelsllmsgsm8kimprove
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time, optimizing reasoning capabilities during training remains challenging. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution and optimizes it via variational approaches. LaTRO enables LLMs to concurrently improve both their reasoning process and ability to evaluate reasoning quality, without requiring external feedback or reward models. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures. On GSM8K, LaTRO improves zero-shot accuracy by an average of 12.5% over base models and 9.6% over supervised fine-tuning across Phi-3.5-mini, Mistral-7B, and Llama-3.1-8B. Our findings suggest that pre-trained LLMs possess latent reasoning capabilities that can be unlocked and enhanced through our proposed optimization approach in a self-improvement manner. The code of LaTRO is available at \url{https://github.com/SalesforceAIResearch/LaTRO}.

discussion (0)

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

Forward citations

Cited by 9 Pith papers

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

  1. Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

    cs.AI 2026-07 conditional novelty 6.0

    A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to...

  2. Unsupervised Causal Abstractions Discovery

    cs.LG 2026-06 unverdicted novelty 6.0

    Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.

  3. LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck

    cs.CV 2026-06 unverdicted novelty 6.0

    LaME performs latent multimodal embedding reasoning with K learnable reason tokens in a weakly supervised information bottleneck, matching some explicit CoT models while running 60x faster.

  4. LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation

    cs.IR 2026-05 unverdicted novelty 6.0

    LASAR uses two-stage supervised training plus reinforcement learning to ground semantic IDs, align latent reasoning trajectories to CoT hidden states via KL divergence, and adaptively choose reasoning depth, halving a...

  5. Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning

    cs.RO 2026-02 unverdicted novelty 6.0

    R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.

  6. When are likely answers right? On Sequence Probability and Correctness in LLMs

    stat.ML 2026-06 unverdicted novelty 5.0

    Higher sequence probability predicts correctness across different answers in a dataset but does not reliably improve accuracy when decoding methods or hyperparameters are changed, nor does it indicate correctness for ...

  7. VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

    cs.LG 2026-02 unverdicted novelty 5.0

    VI-CuRL stabilizes verifier-independent RL for LLM reasoning via confidence-guided curriculum that reduces action and problem variance, with a claimed proof of asymptotic unbiasedness and empirical gains over baselines.

  8. 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.

  9. Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

    cs.AI 2025-03 unverdicted novelty 5.0

    The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.