ARXIV:2601.19588 · LLM DOMAIN ADAPTATION · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

arXiv

Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum. Widely adopted knowledge distillation methods often devolve into coarse-grained mimicry, where the student model inefficiently targets its own weaknesses…

METHOD

Full abstract

Adapting Large Language Models (LLMs) to specialized domains without human-annotated data is a crucial yet formidable challenge. Widely adopted knowledge distillation methods often devolve into coarse-grained mimicry, where the student model inefficiently targets its own weaknesses and risks inheriting the teacher's reasoning flaws. This exposes a critical pedagogical dilemma: how to devise a reliable curriculum when the teacher itself is not an infallible expert. Our work resolves this by capitalizing on a key insight: while LLMs may exhibit fallibility in complex, holistic reasoning, they often exhibit high fidelity on focused, atomic sub-problems. Based on this, we propose Divergence-Guided Reasoning Curriculum (DGRC), which constructs a learning path from atomic knowledge to reasoning chains by dynamically deriving two complementary curricula from disagreements in reasoning pathways. When a student and teacher produce conflicting results, DGRC directs the teacher to perform a diagnostic analysis: it analyzes both reasoning paths to formulate atomic queries that target the specific points of divergence, and then self-answers these queries to create high-confidence atomic question-answer pairs. These pairs then serve a dual purpose: (1) providing an atomic curriculum to rectify the student's knowledge gaps, and (2) serving as factual criteria to filter the teacher's original reasoning chains, yielding a verified CoT curriculum that teaches the student how to integrate atomic knowledge into complete reasoning paths. Experiments across the medical and legal domains on student models of various sizes demonstrate the effectiveness of our DGRC framework. Notably, our method achieves a 7.76% relative improvement for the 1.5B student model in the medical domain over strong unlabeled baseline.

RESULT

ScienceToStartup currently rates this 6.0/10 on the public viability pass. When a student and teacher produce conflicting results, DGRC directs the teacher to perform a diagnostic analysis: it analyzes both reasoning paths to formulate…

WHY NOW

LLM Domain Adaptation moved forward this cycle; last verified April 2026. Public score 6.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score6.0

PainAdapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2601.19588 · LLM DOMAIN ADAPTATION · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

arXiv

Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

LLM Domain Adaptation moved forward this cycle; last verified April 2026. Public score 6.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score6.0

PainAdapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2601.19588

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Parse run linked

A document parse run is attached to this paper.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon file20 anchorsderived fallback40 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

6.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

LLM Domain Adaptation moved forward this cycle; last verified April 2026. Public score 6.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum. Widely adopted knowledge distillation methods often devolve into coarse-grained mimicry, where the student model inefficiently targets its own weaknesses and risks inheriting the teacher's reasoning flaws.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Adapting Large Language Models (LLMs) to specialized domains without human-annotated data is a crucial yet formidable challenge. Widely adopted knowledge distillation methods often devolve into coarse-grained mimicry, where the student model inefficiently targets its own weaknesses and risks inheriting the teacher's reasoning flaws.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 6.0/10 on the public viability pass. When a student and teacher produce conflicting results, DGRC directs the teacher to perform a diagnostic analysis: it analyzes both reasoning paths to formulate atomic queries that target the specific points of divergence, and then self-answers these queries to create high-confidence atomic question-answer pairs.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
LLM Domain Adaptation moved forward this cycle; last verified April 2026. Public score 6.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linkedDocument parse run

Markets

LLM Domain Adaptation

Competitors

not indexed

Competitive landscape

Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.

Segment

LLM Domain Adaptation

Adoption evidence

No public code link in the paper record yet

Commercial read

6.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2601.19588 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(40)

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

2025Run-Ze Fan, Zengzhi Wang et al.

Solving Formal Math Problems by Decomposition and Iterative Reflection

2025Yichi Zhou, Jianqiu Zhao et al.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

2025Gheorghe Comanici, Eric Bieber et al.

Synthetic Data RL: Task Definition Is All You Need

2025Yiduo Guo, Zhen Guo et al.

Qwen3 Technical Report

2025An Yang, Anfeng Li et al.

Scaling Laws of Synthetic Data for Language Models

2025Zeyu Qin, Qingxiu Dong et al.

No Need for Explanations: LLMs can implicitly learn from mistakes in-context

2025Lisa Alazraki, Maximilian Mozes et al.

Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering

2025Yinghao Hu, Leilei Gan et al.

Toward expert-level medical question answering with large language models

2025Karan Singhal, Tao Tu et al.

ProgCo: Program Helps Self-Correction of Large Language Models

2025Xiaoshuai Song, Yanan Wu et al.

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

2025Adam Suma, Samuel Dauncey

Qwen2.5 Technical Report

2024Qwen An Yang, Baosong Yang et al.

FinLlama: LLM-Based Financial Sentiment Analysis for Algorithmic Trading

2024Giorgos Iacovides, Thanos Konstantinidis et al.

HybridFlow: A Flexible and Efficient RLHF Framework

2024Guangming Sheng, Chi Zhang et al.

The Llama 3 Herd of Models

2024Abhimanyu Dubey, Abhinav Jauhri et al.

Gemma 2: Improving Open Language Models at a Practical Size

2024Gemma Team Morgane Riviere, Shreya Pathak et al.

Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching

2024Xiaoying Zhang, Baolin Peng et al.

LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

2024Yaowei Zheng, Richong Zhang et al.

A Survey on Knowledge Distillation of Large Language Models

2024Xiaohan Xu, Ming Li et al.

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

2024Zhihong Shao, Peiyi Wang et al.

Showing 20 of 40 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkTailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility

6.0

Prior WorkThinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance

6.0

Prior WorkCurriculum Learning-Guided Progressive Distillation in Large Language Models

6.0

Extension

Builds On ThisFrom Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning

3.0

Builds On ThisRevealing Algorithmic Deductive Circuits for Logical Reasoning

3.0

Commercially relevant

Higher ViabilityDistilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding

7.0

Higher ViabilityReasoning-Driven Multimodal LLM for Domain Generalization

7.0

Higher ViabilityCog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems

8.0

Higher ViabilityCoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation

7.0

Higher ViabilityLearning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning

7.0

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2601.19588
Route: /paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation
Active tab: read
Artifact: from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation/paper-pack
REST build passport API/api/v1/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "41921691-9525-4dd0-86f7-b0dc93335aed",
  "arxiv_id": "2601.19588",
  "canonical_route": "/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation",
  "endpoints": {
    "paper_pack": "/api/v1/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation/paper-pack",
    "build_passport": "/api/v1/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation

stale

Proof freshness: stale
Proof status: unverified
Display score: 6/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

Canonical ID from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation | Route /paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2601.19588"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation",
  "normalized_query": "2601.19588",
  "route": "/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation",
  "paper_ref": "from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

/buildability/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation

Watchwatch

Subject: From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation

Paper ref

from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation

arXiv id

2601.19588

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

f3b9f3fd8017e4f0cfdd142deff4a99c08315200ad5f068bbae0797ab76f9027

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

Source proof

Visual citation anchors from the paper document graph.

20 anchors

proof blockPage 2282%

This equation captures one of the core mathematical components of the system. ing set. For each problem, the teacher generates a single response (K = 1), while the student produces eight diverse res

Page and bbox are available; crop image is pending.

proof blockPage 2290%

This equation defines the score or evaluation function that determines model quality.

Page and bbox are available; crop image is pending.

proof blockPage 2282%

This equation captures one of the core mathematical components of the system. (J = 8). The teacher’s response is paired with each of the student’s eight responses to diagnose

Page and bbox are available; crop image is pending.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation#webpage",
      "url": "https://sciencetostartup.com/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation",
      "name": "From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation",
      "description": "Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation#scholarlyArticle",
      "headline": "From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation",
      "description": "Adapting large language models to specialized domains without labeled data using a divergence-guided reasoning curriculum.",
      "url": "https://sciencetostartup.com/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation",
      "sameAs": "https://arxiv.org/abs/2601.19588",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2601.19588"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-01-27T13:23:40.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "97f22904adc7692f170d1844319a888c06488f55"
          },
          "url": "https://www.semanticscholar.org/paper/97f22904adc7692f170d1844319a888c06488f55"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c116dd5aac94385dcd8626e4f4991d99e9ce5451"
          },
          "url": "https://www.semanticscholar.org/paper/c116dd5aac94385dcd8626e4f4991d99e9ce5451"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "39d9c3f1cd4bd5069713e50dc7301570575fc055"
          },
          "url": "https://www.semanticscholar.org/paper/39d9c3f1cd4bd5069713e50dc7301570575fc055"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e98e1f50c1892c08ecb19d27df4f9c7d97fd9353"
          },
          "url": "https://www.semanticscholar.org/paper/e98e1f50c1892c08ecb19d27df4f9c7d97fd9353"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
          },
          "url": "https://www.semanticscholar.org/paper/d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "44110e5f9c441bdb300b99995ac48989198ac350"
          },
          "url": "https://www.semanticscholar.org/paper/44110e5f9c441bdb300b99995ac48989198ac350"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7d282da198488f862db63e5b0f8b469e4f4a44eb"
          },
          "url": "https://www.semanticscholar.org/paper/7d282da198488f862db63e5b0f8b469e4f4a44eb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5b744751d5d98fe9ba2036eeedea0b6a22dc69b7"
          },
          "url": "https://www.semanticscholar.org/paper/5b744751d5d98fe9ba2036eeedea0b6a22dc69b7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b34c0b0169925a6c7f14e3de9764ed9505f30de3"
          },
          "url": "https://www.semanticscholar.org/paper/b34c0b0169925a6c7f14e3de9764ed9505f30de3"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0763d6c644b80aba0ee66706c4de88aed2d1d126"
          },
          "url": "https://www.semanticscholar.org/paper/0763d6c644b80aba0ee66706c4de88aed2d1d126"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "88aa6b1f37d1fd8e0a40499ce9bb87873f03aaa8"
          },
          "url": "https://www.semanticscholar.org/paper/88aa6b1f37d1fd8e0a40499ce9bb87873f03aaa8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d798dea2a4e995e08de033809ec3fd63c53d8b46"
          },
          "url": "https://www.semanticscholar.org/paper/d798dea2a4e995e08de033809ec3fd63c53d8b46"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f2d0f3d47ae850f49a58f4977393bd0025af4bec"
          },
          "url": "https://www.semanticscholar.org/paper/f2d0f3d47ae850f49a58f4977393bd0025af4bec"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "40e8af970329135ec95057d73e239dab805ad128"
          },
          "url": "https://www.semanticscholar.org/paper/40e8af970329135ec95057d73e239dab805ad128"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ec2ce4e38af8bc82f1b8928ba51a84911bad0cc6"
          },
          "url": "https://www.semanticscholar.org/paper/ec2ce4e38af8bc82f1b8928ba51a84911bad0cc6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "508f50f171b4aee6cbc573da1bed0472a86eaa8b"
          },
          "url": "https://www.semanticscholar.org/paper/508f50f171b4aee6cbc573da1bed0472a86eaa8b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d5d7b26dbdf09737878644530b226a79c9f43bfb"
          },
          "url": "https://www.semanticscholar.org/paper/d5d7b26dbdf09737878644530b226a79c9f43bfb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "94db8a625418800c8ae7b48157a9cad1c8129051"
          },
          "url": "https://www.semanticscholar.org/paper/94db8a625418800c8ae7b48157a9cad1c8129051"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "35b142ea69598e6241f0011312128031df55895c"
          },
          "url": "https://www.semanticscholar.org/paper/35b142ea69598e6241f0011312128031df55895c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ff5f0c5b6905a8c4b361a625b450e9ab417fa854"
          },
          "url": "https://www.semanticscholar.org/paper/ff5f0c5b6905a8c4b361a625b450e9ab417fa854"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 6
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "LLM Domain Adaptation"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "LLM Domain Adaptation",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "From Atoms to Chains: Divergence-Guided Reasoning Curriculum",
          "item": "https://sciencetostartup.com/paper/from-atoms-to-chains-divergence-guided-reasoning-curriculum-for-unlabeled-llm-domain-adaptation"
        }
      ]
    }
  ]
}

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(40)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(40)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline