Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
Updated 32 min ago · first seen 11 Sept 2026
paper_01M294G4BJ6KMNFBE1K2EWAJBG
- Published
- 11 Sept 2026
- T1 · 6 h ago
- arXiv
- 2609.10745
- T1 · 6 h ago
- Category
- cs.CL
- T1 · 6 h ago
Abstract
Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on rare entities, but prior work measures rarity primarily through popularity-based metrics such as pageviews. We broaden this view using knowledge-graph structural metrics that capture how well an entity is documented and connected. These metrics identify many rare entities that popularity metrics miss. Across the resulting rare-entity slices, state-of-the-art accuracy drops by 15.4-39.9%, showing that different rarity definitions expose different failure modes. To address these failures, we introduce a simple, training-free framework in which a reasoning-capable vision-language model iteratively searches and reasons over Wikipedia, gathering evidence dynamically. Controlled experiments show that reasoning and retrieval are complementary. Reasoning alone does not significantly improve accuracy on rare entities. Retrieval without reasoning improves rare-entity accuracy but can hurt overall accuracy. Their combination performs best. On MERLIN, a multilingual multimodal entity linking benchmark over five languages (Hindi, Indonesian, Japanese, Tamil, Vietnamese), our best system improves over the state of the art by 6.9% overall and by up to 23.3% on rare-entity slices. We release MERLIN-Rare, rare-entity test slices for targeted evaluation, with our framework.
Authors 3
Parinthapat Pengpun, Simran Khanuja, Graham Neubig
Specification
- Official page
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
- Arxiv announce type
- new
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
- arXiv id
- 2609.10745
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
- Categories
- cs.CL
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
- Github repo
- neulab/think-before-you-link
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Hf paper url
- https://huggingface.co/papers/2609.10745
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Github stars
- 2
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 32 min agomedium
- Hf comments
- 2
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 32 min agomedium
- Upvotes
- 2
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 32 min agomedium
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
- Primary category
- cs.CL
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
- Published
- 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
14
Source tiers
T1T29 / 5
Freshest observation
32 min ago
Conflicts
6 flagged
No models linked to this paper yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Abstract
Abstractabstract1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on rare entities, but prior work measures rarity primarily through popularity-based metrics such as pageviews. We broaden this view using knowledge-graph structural metrics that capture how well an entity is documented and connected. These metrics identify many rare entities that popularity metrics miss. Across the resulting rare-entity slices, state-of-the-art accuracy drops by 15.4-39.9%, showing that different rarity definitions expose different failure modes. To address these failures, we introduce a simple, training-free framework in which a reasoning-capable vision-language model iteratively searches and reasons over Wikipedia, gathering evidence dynamically. Controlled experiments show that reasoning and retrieval are complementary. Reasoning alone does not significantly improve accuracy on rare entities. Retrieval without reasoning improves rare-entity accuracy but can hurt overall accuracy. Their combination performs best. On MERLIN, a multilingual multimodal entity linking benchmark over five languages (Hindi, Indonesian, Japanese, Tamil, Vietnamese), our best system improves over the state of the art by 6.9% overall and by up to 23.3% on rare-entity slices. We release MERLIN-Rare, rare-entity test slices for targeted evaluation, with our framework. | → current | current | arXiv (Atom API + RSS)T1 | high | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
- New paperPaperThink Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
New paper: Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
arxiv
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| arXiv (Atom API + RSS) | rss.arxiv.org/rss/cs.CL | feed | T1· Official | 5 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/papers | listing | T2· Quality secondary | 32 min ago | 6 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.