cd /news/machine-learning/teller-dual-path-iterative-preferenc… · home topics machine-learning article
[ARTICLE · art-84189] src=arxiv.org ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking

Researchers introduced TELLER, a dual-path iterative preference optimization method for table entity linking, which improves accuracy on the TableInstruct entity-linking subset from 94.35% to 94.50% via a direct-answer path and from 92.90% to 92.95% via a reasoning path, and on MammoTab V2 from 87.59% to 88.20% and from 79.09% to 81.85%, respectively. The method, detailed in arXiv:2607.28680v1, addresses static training supervision by refreshing preference data with residual errors and applying length-normalized regularized preference optimization.

read1 min views1 publishedAug 3, 2026

arXiv:2607.28680v1 Announce Type: new Abstract: 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.

── more in #machine-learning 4 stories · sorted by recency
── more on @teller 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/teller-dual-path-ite…] indexed:0 read:1min 2026-08-03 ·