Paper Citation Record · LEDGER

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation

As of 10 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 1 inbound Pith citation observation for arXiv:2502.05911.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.05911 v1

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:31:59.951364Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T01:23:01.921132Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-18T01:25:34.979210Z

Reference resolution

59 of 59 outbound references displayed

verified exact4
verified fuzzy2
unresolved53
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 31cd75f1-2fa6-4cda-93b0-b13659aa9c99 · outbound

This paper cites RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:32:00.378572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4b5c76b-2b33-428f-baf1-ef36367a6c38 · outbound

This paper cites Efficient Model-agnostic Alignment via Bayesian Persuasion.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Efficient Model-agnostic Alignment via Bayesian Persuasion

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.769377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97cbe8de-681f-4aee-8d13-936e02b17731 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:32:00.508773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 18e2ba56-6341-44c8-b3d0-589e66b514d9 · outbound

This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.775874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4ac8346-95d8-49b3-be49-5d588b7dcc2e · outbound

This paper cites Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.779480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3359a1b-a55b-4c0e-9335-cf2814405e51 · outbound

This paper cites Can AI Assistants Know What They Don't Know?.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Can AI Assistants Know What They Don't Know?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.783337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac8b7d7f-9149-49d4-9e40-d617761dbb7f · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.786697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c26d678-0727-4566-88da-af77e191c3f6 · outbound

This paper cites Knowledge Neurons in Pretrained Transformers.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Knowledge Neurons in Pretrained Transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.789363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3420928a-3a50-460c-b3a7-1425a68ea300 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.792195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e144b74d-ab38-48a2-b0b8-32305bcabc2c · outbound

This paper cites The Llama 3 Herd of Models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.794895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1b452a8-a336-425d-a42a-a9cbfff375d0 · outbound

This paper cites Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.798068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56032f7f-3a9f-4bf5-8f60-5a264f06f9f6 · outbound

This paper cites Successor Heads: Recurring, Interpretable Attention Heads In The Wild.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.801158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8282045c-f268-41fc-8588-fc6203cc46c3 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Measuring Massive Multitask Language Understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.804096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a7a9c2d-3f2f-4731-af89-5c472a7fa147 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation LoRA: Low-Rank Adaptation of Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.807595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf18524-daa3-4e47-a935-8b6e08c0640e · outbound

This paper cites Lora: Low-rank adaptation of large language models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Lora: Low-rank adaptation of large language models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.810829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f0cb3b-5383-4bae-a944-53268445c686 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.813879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 637c8f11-9eae-419c-80e1-cf83d3a797a0 · outbound

This paper cites TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.817364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd7b17a7-b4e3-43e7-9c07-18ca3bd834b9 · outbound

This paper cites HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.820951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fea0eba-5208-4f40-bbe4-ade36c48fcad · outbound

This paper cites Johnson and Joram Lindenstrauss.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Johnson and Joram Lindenstrauss

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.823920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7886acf6-e0f5-4cd5-a930-50db5c6a6460 · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.827763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e847c900-f1ff-4b67-adb6-c42e79d94777 · outbound

This paper cites Unfamiliar Finetuning Examples Control How Language Models Hallucinate.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unfamiliar Finetuning Examples Control How Language Models Hallucinate

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.831137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d274182-0347-4f98-a148-6fc5013bfcfb · outbound

This paper cites Scaling Laws for Neural Language Models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Scaling Laws for Neural Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.834122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a48ee927-a83c-4218-8823-ba6bcaf698fb · outbound

This paper cites GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.840500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74d034ec-774d-4d25-876f-f0999b45b9ea · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.842715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f69519e-fed4-4bc7-b23a-0895dcdfcb86 · outbound

This paper cites A Survey on the Honesty of Large Language Models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation A Survey on the Honesty of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.844845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef876ad-e0c4-4a39-a5bd-2aebf392653c · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:32:00.482230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0e44cc3-ed0f-4761-8386-0274115767e1 · outbound

This paper cites Kuaiji: the First Chinese Accounting Large Language Model.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Kuaiji: the First Chinese Accounting Large Language Model

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:32:00.234005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 25960b7c-3f1e-4010-b469-52d0a7dfbc28 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.852410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 397fd5d1-786b-4a54-bb40-3aa001d159e3 · outbound

This paper cites GPT-4 Technical Report.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation GPT-4 Technical Report

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.855783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c1cc5c3-ed39-405e-9f49-0550080fb395 · outbound

This paper cites Training language models to follow instructions with human feedback.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Training language models to follow instructions with human feedback

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:32:00.468362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cc7f3b43-1bf4-409a-9bdb-0e9295edce31 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:32:00.459322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7750d40b-369a-4ba5-b095-73d5dae974dc · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:32:00.451318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8865962-6189-4098-a9de-b200789aee2a · outbound

This paper cites Identifying Semantic Induction Heads to Understand In-Context Learning.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Identifying Semantic Induction Heads to Understand In-Context Learning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.869479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d1cefa-0a74-4185-9aad-9a37d29062d8 · outbound

This paper cites Learning or Self-aligning? Rethinking Instruction Fine-tuning.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Learning or Self-aligning? Rethinking Instruction Fine-tuning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.872964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65f3cb4c-1b59-4f7e-b1bc-d7bbeb5920f2 · outbound

This paper cites Learning Dynamics of LLM Finetuning.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Learning Dynamics of LLM Finetuning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.876018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7066f076-15fe-4743-a4dc-7c2835b23a56 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.879702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe3773f-abb7-4a73-9c47-d90c3ee23680 · outbound

This paper cites The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.882927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54c2efaf-0d3d-4cb5-985e-80c3d9a9097b · outbound

This paper cites GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.886209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aafbbff8-f7fc-4085-b8bb-09e499b67b8c · outbound

This paper cites Knowledge Verification to Nip Hallucination in the Bud.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Knowledge Verification to Nip Hallucination in the Bud

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.890019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f22eb664-662e-4ebd-97df-30ff5b35a66c · outbound

This paper cites Uncertainty Aware Learning for Language Model Alignment.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Uncertainty Aware Learning for Language Model Alignment

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.893923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a11969d5-99cc-4bb6-bc41-ced495ba74b8 · outbound

This paper cites Know your limits: A survey of abstention in large language models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Know your limits: A survey of abstention in large language models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:32:00.440937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7203753f-3149-4d15-bb44-1ec0e10bbe41 · outbound

This paper cites Do Llamas Work in English? On the Latent Language of Multilingual Transformers.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Do Llamas Work in English? On the Latent Language of Multilingual Transformers

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.899901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f22ed801-3d0a-4800-ab1f-77523a0e600e · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.902481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11ccd4aa-1365-4999-b946-c001122c4f81 · outbound

This paper cites LESS: Selecting Influential Data for Targeted Instruction Tuning.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation LESS: Selecting Influential Data for Targeted Instruction Tuning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.904624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7664ad69-dbd1-4a3c-b4f9-f1cd953e8518 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:32:00.430316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a99bae8a-575c-4940-ac76-c709c416c0ae · outbound

This paper cites Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.910590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc5bfc07-519f-404d-9dbc-fabd1755de94 · outbound

This paper cites Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:32:00.046467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 12886857-c64a-46bf-bb63-0f7df68c5661 · outbound

This paper cites SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.916976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27cadcd8-87f4-4fdb-8557-e5daf82216dd · outbound

This paper cites Alignment for Honesty.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Alignment for Honesty

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.920040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93b4e325-2e03-4e26-87a0-b2cd9d336945 · outbound

This paper cites xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.923195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 873a2a21-b63a-4e57-9382-109f4d6f1500 · outbound

This paper cites Neuron-Level Knowledge Attribution in Large Language Models.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Neuron-Level Knowledge Attribution in Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.926169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67d847bb-b7db-4638-bd13-7edf1ba7dc52 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.929482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f993a29d-7435-4afa-8b80-77269f7066e6 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:32:00.415351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 447ebd98-c33a-494a-9478-a25c9a8450c5 · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.935038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1fb5ae-d453-4cbb-b173-f9e0cd0da1c6 · outbound

This paper cites Dataset Condensation with Gradient Matching.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Dataset Condensation with Gradient Matching

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.938121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27e868bd-7e2a-4925-ad71-684eed03445d · outbound

This paper cites an unresolved cited work.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:32:00.405884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 407f7128-254f-49bd-9c51-ffdb39be292e · outbound

This paper cites Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:31:59.995292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c254be1d-af1e-49de-b343-610620c637ca · outbound

This paper cites online" 'onlinestring :=.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation online" 'onlinestring :=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.948359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 902c6faa-59bb-49be-b97e-97d82bd793b9 · outbound

This paper cites write newline.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation write newline

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T17:31:59.951364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1e66bb30-e92b-406d-84a9-65e7d7589ac1 · inbound

Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation cites this paper.

Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-18T01:25:34.981249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.