pith. sign in
Pith Number

pith:OUDWHWEU

pith:2026:OUDWHWEUIP57XMCUMOAYY3MKL7
not attested not anchored not stored refs pending

How Language Models Process Negation

Jonathan May, Robin Jia, Tianyi Zhou, Zhejian Zhou

Language models process negation by constructing representations of negative phrases more than by suppressing positives.

arxiv:2605.03052 v2 · 2026-05-04 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{OUDWHWEUIP57XMCUMOAYY3MKL7}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We apply a range of observational and causal interpretability techniques on Mistral-7B and Llama-3.1-8B to show that models implement both mechanisms, with the 'constructive' mechanism being more prominent.

C2weakest assumption

That the observational and causal interpretability techniques (such as attention ablation and activation analysis) accurately isolate and identify the specific mechanisms responsible for negation processing without confounding effects from other model components.

C3one line summary

LLMs implement both attention-based suppression and constructive representations for negation, with construction dominant, despite poor accuracy from late-layer attention shortcuts.

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-06-02T01:03:16.146064Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

750763d89443fbfbb05463818c6d8a5fc7b6f0892d3b00df9f89237a8b4050c9

Aliases

arxiv: 2605.03052 · arxiv_version: 2605.03052v2 · doi: 10.48550/arxiv.2605.03052 · pith_short_12: OUDWHWEUIP57 · pith_short_16: OUDWHWEUIP57XMCU · pith_short_8: OUDWHWEU
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/OUDWHWEUIP57XMCUMOAYY3MKL7 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 750763d89443fbfbb05463818c6d8a5fc7b6f0892d3b00df9f89237a8b4050c9
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "3f7d4817f55118373e90a8f549904e01dab05f60d99547f0ba79e90118fd7d0c",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-04T18:17:05Z",
    "title_canon_sha256": "d3761b2174bae54d4638480ef8a504bd600dacbb661389e838b37b4ae07ecbaa"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03052",
    "kind": "arxiv",
    "version": 2
  }
}