HFEPX · Eval paper review
Boyi Zeng, Yiqin Hao, He Li, Shixiang Song +7 more
Published
Feb 9, 2026
Citations
0
Trust level
Low
Usefulness score
25/100 (Low)
Extraction confidence
45% (Low)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Mar 10, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this as background context only. Do not make protocol decisions from this page alone.
Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.
Best use
Background context only
Use if you need
A secondary eval reference to pair with stronger protocol papers.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
The available metadata is too thin to trust this as a primary source.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explores an alternative axis: increasing per-token computation without expanding parameters, by internalizing latent Chain-of-Thought (CoT) into pretraining. We propose Pretraining with Token-Level Adaptive Latent CoT (adaptive latent CoT), where the model generates a variable-length latent CoT trajectory before emitting each token -- allocating longer trajectories to difficult tokens and shorter (or even zero) trajectories to easy ones. Importantly, this behavior emerges naturally from one-stage pretraining on general text and reduces computation in both training and inference via token-wise adaptive halting. Experiments with Llama architectures show that adaptive latent CoT consistently improves language modeling perplexity and broad downstream accuracy, even with fewer training FLOPs than prior recurrent baselines.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
None explicit
No explicit feedback protocol extracted.
"Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs."
Automatic Metrics
Includes extracted eval setup.
"Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs."
Not reported
No explicit QC controls found.
"Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs."
Not extracted
No benchmark anchors detected.
"Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs."
Accuracy, Perplexity
Useful for evaluation criteria comparison.
"Experiments with Llama architectures show that adaptive latent CoT consistently improves language modeling perplexity and broad downstream accuracy, even with fewer training FLOPs than prior recurrent baselines."
No benchmark or dataset names were extracted from the available abstract.
Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
No explicit human feedback protocol detected.
Evaluation mode is explicit
Detected: Automatic Metrics
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
No benchmark/dataset anchor extracted from abstract.
Metric reporting is present
Detected: accuracy, perplexity
