Pith Number

pith:PDZIM2VJ

pith:2026:PDZIM2VJNR2HFKP5EVFKSXYSSB

not attested not anchored not stored refs resolved

LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots

Bo Zheng, Chuan Yu, Haoran Sun, Jian Xu, Xiaotie Deng, Xinrui Song, Xinyu Zhang, Xu Chu, Zhaohua Chen, Zhilin Zhang

LERA combines embedding filters with LLM logits for relevance and applies a critical-value payment to run truthful ad auctions inside generative chatbots.

arxiv:2605.16474 v1 · 2026-05-15 · cs.IR · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PDZIM2VJNR2HFKP5EVFKSXYSSB}

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

The LERA framework ensures truthfulness for utility-maximizing advertisers by using a critical-value payment rule that accounts for both the coarse-filtering and fine-ranking thresholds.

C2weakest assumption

The assumption that logits produced by a carefully designed prompt to the LLM constitute reliable, unbiased organic relevance scores that can be directly combined with bids without introducing new commercial misinterpretation or repetitive insertion problems.

C3one line summary

LERA is a retrieve-then-generate auction system that refines ad candidate ranking with LLM logits and applies a threshold-aware critical-value payment rule to maintain truthfulness in chatbot ad insertion.

References

66 extracted · 66 resolved · 3 Pith anchors

[1] Position auctions in ai-generated content.arXiv preprint arXiv:2506.03309, 2025 2025

[2] Uncovering chatgpt’s capabilities in recommender systems 2023

[3] Deepseek-v3.2: Pushing the frontier of open large language models 2025

[4] Auctions with llm summaries 2024

[5] Mechanism design for large language models 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:02:23.875842Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

78f2866aa96c7472a9fd254aa95f12906811aa96630b984b5438f84ee01ff87d

Aliases

arxiv: 2605.16474 · arxiv_version: 2605.16474v1 · doi: 10.48550/arxiv.2605.16474 · pith_short_12: PDZIM2VJNR2H · pith_short_16: PDZIM2VJNR2HFKP5 · pith_short_8: PDZIM2VJ

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB \
  | 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: 78f2866aa96c7472a9fd254aa95f12906811aa96630b984b5438f84ee01ff87d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c0e6899192d86eedfa53dc0864ba55582516ef68e5f80ff21c2a80b1e5502267",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-15T15:39:30Z",
    "title_canon_sha256": "3a4bd550581a91b0cebd406dbfa7b4bd4e876dbc07bfc14eac9dc4b841ea2d55"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16474",
    "kind": "arxiv",
    "version": 1
  }
}