Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics

Jian Gu, Hongyu Zhang, Chunyang Chen, Aldeida Aleti

Published

Oct 15, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

20% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 18, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Should you rely on this paper?

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.

Best use

Background context only

Use if you need

Background context only.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream. Between them, existing methods reuse a fixed lens or treat states as a point cloud, and neither reads a state as the model does. We argue that every hidden state has a native reference frame, induced by the layers that remain and adaptive to the context. Lexical reference frames approximate it in a model-native and context-aware way, reading a state through the remaining layers with a given number of rounds of attention between positions and a typical attention output for the rest, fitting nothing to the model's output. No lens with fixed directions per layer can reach a mean cosine with the native frame's lexical readouts above the square root of their coherence, 0.30 and 0.35 at mid-depth of SmolLM3-3B and OLMo3-7B. LexFrame[1], of order 1, reaches 0.97 and 0.97, and its readings are on average within 0.16 and 0.15 nats of the model's output. Its coefficient differences attribute predictions more faithfully than attribution patching, and its lexical basis steers predictions while sparing other tokens. On average, its readings settle on the model's top token over the final 0.82 and 0.81 of the layers, those of lenses over at most 0.11. These frames thus make every hidden state readable, attributable and steerable.

What we could verify

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.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream."

Quality Controls

missing

Not reported

No explicit QC controls found.

"The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream."

Reported Metrics

partial

Coherence

Useful for evaluation criteria comparison.

"No lens with fixed directions per layer can reach a mean cosine with the native frame's lexical readouts above the square root of their coherence, 0.30 and 0.35 at mid-depth of SmolLM3-3B and OLMo3-7B."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

coherence
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream.
  • Between them, existing methods reuse a fixed lens or treat states as a point cloud, and neither reads a state as the model does.
  • We argue that every hidden state has a native reference frame, induced by the layers that remain and adaptive to the context.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream.
  • Between them, existing methods reuse a fixed lens or treat states as a point cloud, and neither reads a state as the model does.
  • We argue that every hidden state has a native reference frame, induced by the layers that remain and adaptive to the context.

Why it matters for eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • 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: coherence