Pith Number

pith:RGCX4YG6

pith:2026:RGCX4YG6TIPMIEEBXOLKTMRO5K

not attested not anchored not stored refs resolved

Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering

Benjamin Charles Germain Lee, Jevin West, Maryam Amirizaniani, Nicholas Weber

Reinforcement learning trains LLMs to infer implicit user intent from single-turn questions and generate better-aligned personalized answers.

arxiv:2605.12645 v1 · 2026-05-12 · cs.CL · 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{RGCX4YG6TIPMIEEBXOLKTMRO5K}

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

Through experiments on the LaMP-QA benchmark across six models, IAP consistently outperforms all baselines, achieving an average macro-score gain of around 7.5% over the strongest competitor.

C2weakest assumption

That a tag-based schema combined with a personalized reward function can reliably infer implicit intent from single-turn questions and optimize generation paths to produce better-aligned answers without multi-turn context or user profiles.

C3one line summary

IAP uses RL to train LLMs to explicitly infer and apply implicit user intent in single-turn personalized QA, achieving ~7.5% average macro-score gains over baselines on LaMP-QA.

References

91 extracted · 91 resolved · 9 Pith anchors

[1] Second Conference on Language Modeling , year=

[2] Yixin Ye and Zhen Huang and Yang Xiao and Ethan Chern and Shijie Xia and Pengfei Liu , booktitle=. 2025 , url= 2025

[3] Search-R1: Training 2025

[4] Legal Mathematical Reasoning with LLM s: Procedural Alignment through Two-Stage Reinforcement Learning 2025 · doi:10.18653/v1/2025.findings-emnlp.84

[5] Beyond Guilt: Legal Judgment Prediction with Trichotomous Reasoning 2025 · doi:10.18653/v1/2025.findings-emnlp.95

Receipt and verification

First computed	2026-05-18T03:09:59.860930Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

89857e60de9a1ec41081bb96a9b22eeaa39ecb81e7ae0e10f885c80ea4faaf8b

Aliases

arxiv: 2605.12645 · arxiv_version: 2605.12645v1 · doi: 10.48550/arxiv.2605.12645 · pith_short_12: RGCX4YG6TIPM · pith_short_16: RGCX4YG6TIPMIEEB · pith_short_8: RGCX4YG6

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/RGCX4YG6TIPMIEEBXOLKTMRO5K \
  | 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: 89857e60de9a1ec41081bb96a9b22eeaa39ecb81e7ae0e10f885c80ea4faaf8b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a30eeb0146adc8ec63861c7fd2a5ef2ba6b1dbef9386d8dbd7708de408fd50e0",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-12T18:38:05Z",
    "title_canon_sha256": "47a85d26e73ac3faf8d84e7091771c2d3b8394f5a693d7e3b9d3ae06dfd0b301"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12645",
    "kind": "arxiv",
    "version": 1
  }
}