TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking
Quick Answer
TELLER introduces a dual-path iterative preference optimization for table entity linking, enhancing accuracy on benchmarks like TableInstruct (from 94.35% to 94.50%) and MammoTab V2 (from 87.59% to 88.20%).
Quick Take
This model adapts preference data dynamically, addressing static supervision limitations and improving reasoning generation rates.
Key Points
- TELLER optimizes entity linking by learning from errors and reasoning.
- Direct-answer path accuracy improved from 94.35% to 94.50% on TableInstruct.
- MammoTab V2 accuracy increased from 87.59% to 88.20% using TELLER.
- Reasoning path accuracy rose from 79.09% to 81.85% on MammoTab V2.
- Iterative preference learning enhances both concise predictions and reasoning.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipelines that retain either compact or extensive table content as contextual evidence, and then formulate entity linking as a language generation task for instruction-tuned models; recent systems further incorporate explicit reasoning to disambiguate challenging mentions. However, their training supervision is usually static: fixed preference data cannot adapt to the residual errors of an evolving model, while variations in reasoning length can bias sequence-level preference learning. To address these limitations, we present TELLER: Table Entity Linking through Learning from Errors and Reasoning. We first retrieve and rank Wikidata candidates and retain reduced table evidence in the prompt. The direct-answer path applies iterative direct preference optimization and refreshes its preference data with residual errors from the updated model. The reasoning path uses filtered and compressed chain-of-thought rationales for supervised fine-tuning, followed by our iterative length-normalized regularized preference optimization. On the TableInstruct entity-linking subset, the direct-answer path improves accuracy from 94.35\% to 94.50\%; on the MammoTab V2 evaluation set, it improves accuracy from 87.59\% to 88.20\%. The reasoning path improves accuracy from 92.90\% to 92.95\% on TableInstruct and from 79.09\% to 81.85\% on MammoTab V2, while maintaining high rates of complete reasoning generation. These results show that iterative preference learning benefits both concise entity prediction and explicit reasoning.
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.28680 [cs.CL] |
| (or arXiv:2607.28680v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.28680 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yixin Peng [view email]
[v1]
Wed, 29 Jul 2026 18:08:26 UTC (1,234 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.