cd /news/large-language-models/tether-training-free-elastic-toc-anc… · home › topics › large-language-models › article
[ARTICLE · art-173012] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

TETHER: Training-Free, Elastic, ToC-Anchored Hierarchy Extraction and Recovery in Design-Driven Long Documents

A new arXiv paper (2611.24960v1) introduces TETHER, a training-free framework that uses a document's Table of Contents as a structural prior to recover hierarchy in design-driven long documents, reporting state-of-the-art zero-shot results on a multilingual benchmark of ESG reports, product manuals and annual reports. TETHER runs a two-stage neuro-symbolic mechanism: a Large Multimodal Model builds a document skeleton from the raw ToC under spatio-semantic constraints, then an anchor-based alignment strategy tethers content blocks to that skeleton. The authors report 90% token reduction and "drastic speedups" over end-to-end baselines, with ablations confirming the framework's architectural irreducibility and stress tests showing resilience to sparse omissions and textual noise.

recommendation

For long, design-heavy documents, build a hierarchy skeleton from the ToC first and align content blocks to it rather than relying on visual cues, which cut tokens 90% in the reported benchmark.

more in playbook: Retrieval and RAG
by read1 min views1 publishedNov 20, 2026

arXiv:2611.24960v1 Announce Type: new Abstract: Converting complex documents into structured knowledge constitutes the critical infrastructure urgently required for deploying Large Language Models (LLMs) in downstream research. However, blind to the Table of Contents (ToC) as a macro-structure, existing bottom-up paradigms rely on localized visual cues, inducing heuristic fragility in high-entropy layouts where visual prominence decouples from logical depth; meanwhile, direct LLM extraction lacks spatial grounding, triggering hallucinations in long contexts. To address this, we introduce TETHER, a training-free framework that elevates the ToC from discarded noise to a vital structural prior, enabling robust adaptation across design-driven long documents. TETHER operates via a two-stage neuro-symbolic mechanism: first, it constructs a document skeleton from the raw ToC using a Large Multimodal Model (LMM) empowered by spatio-semantic constraints; second, it employs an anchor-based alignment strategy to tether content blocks to this skeleton, effectively resolving boundary ambiguities. Evaluated across a multilingual benchmark of ESG reports, product manuals, and annual reports, TETHER delivers highly precise, state-of-the-art (SOTA) zero-shot hierarchy recovery, outperforming deep hierarchical recovery models, dedicated parsers, and general-purpose LMMs. Moreover, stress tests highlight TETHER's resilience to sparse omissions and textual noise, demonstrating that its precise semantic alignment is fundamentally anchored in topological and depth fidelity. Crucially, ablations confirm the framework's architectural irreducibility, while achieving 90% token reduction and drastic speedups over end-to-end baselines, establishing a compelling equilibrium between structural precision and deployment scalability.

── more in #large-language-models 4 stories · sorted by recency
── more on @tether 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/tether-training-free…] indexed:0 read:1min 2026-11-20 · —