Paper Citation Record · LEDGER

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

As of 21 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 10 inbound Pith citation observations for arXiv:2411.12591.

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

pith.paper-citation-record.v1
2411.12591 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T19:35:45.274312Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:10:02.962883Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T17:18:53.747034Z

Reference resolution

49 of 49 outbound references displayed

verified exact0
verified fuzzy19
unresolved28
parse uncertain1
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3e6706d4-3415-4aac-a73f-798fa6a258f8 · outbound

This paper cites GPT-4 Technical Report.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.000081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fccdf2c1-e8fd-4853-8af9-18c9613a300f · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.006364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df722e4-4254-40c7-8c40-9e6bd7845bdd · outbound

This paper cites Hallucination of Multimodal Large Language Models: A Survey.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Hallucination of Multimodal Large Language Models: A Survey

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.012930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 418e0488-da97-4b86-837a-c4819cae40e6 · outbound

This paper cites Visual question answering on image sets.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Visual question answering on image sets

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.204962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d3a42c52-c14f-4e79-8351-059360ab9996 · outbound

This paper cites Rubi: Reducing unimodal biases for visual question answering.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Rubi: Reducing unimodal biases for visual question answering

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.188257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e2bc77d8-2610-458f-b0f9-44570dff61e6 · outbound

This paper cites Gemini 1.5: Unlocking multimodal un- derstanding across millions of tokens of context.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Gemini 1.5: Unlocking multimodal un- derstanding across millions of tokens of context

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.171028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 003119e3-3d0c-488e-9647-a969312f1d80 · outbound

This paper cites Learning to prompt for open-vocabulary ob- ject detection with vision-language model.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Learning to prompt for open-vocabulary ob- ject detection with vision-language model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.042023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dddba74-901b-4687-bc9e-05c453ba19d6 · outbound

This paper cites Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.109156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3a467f93-04ca-4118-8162-befb31904b1a · outbound

This paper cites Complexity-based prompting for multi-step reasoning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Complexity-based prompting for multi-step reasoning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.090078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3ea81aaf-bce2-4f73-8bf6-94b8b0f89cb6 · outbound

This paper cites Hallusionbench: an advanced diagnos- tic suite for entangled language hallucination and visual il- lusion in large vision-language models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Hallusionbench: an advanced diagnos- tic suite for entangled language hallucination and visual il- lusion in large vision-language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.071887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fe1b2a44-f5cc-431c-bf8c-c1c1ae72c523 · outbound

This paper cites Reasoning with language model is planning with world model, 2023.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Reasoning with language model is planning with world model, 2023

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.054274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b710a177-c817-44eb-acd7-d705215ae4f0 · outbound

This paper cites Towards reason- ing in large language models: A survey.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Towards reason- ing in large language models: A survey

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:46.035823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7605b9e2-e2cf-4856-8add-bf8b6aba6039 · outbound

This paper cites FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.077022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48e1db89-2dfe-469c-8d84-36cb4c85c192 · outbound

This paper cites Seed-bench: Bench- marking multimodal large language models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Seed-bench: Bench- marking multimodal large language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.082890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71a2c00d-b5c0-405a-b7ca-4b598b2ab2be · outbound

This paper cites Making Large Language Models Better Reasoners with Step-Aware Verifier.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Making Large Language Models Better Reasoners with Step-Aware Verifier

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.088222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ca54f3-666d-45ec-a171-3ede520f9401 · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Evaluating Object Hallucination in Large Vision-Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.093144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba21dcb-707c-4579-b659-6f34f7ed9736 · outbound

This paper cites HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.098207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47b632c8-6cac-4f46-b534-b63e918fa968 · outbound

This paper cites Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.103211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c6e49f5-f8e6-4e92-ac46-b989b08edcc4 · outbound

This paper cites Mitigating hallucination in large multi-modal models via robust instruction tuning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Mitigating hallucination in large multi-modal models via robust instruction tuning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.109012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4d8b8ae-df91-4644-9f1c-b54758c07750 · outbound

This paper cites Improved baselines with visual instruction tuning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Improved baselines with visual instruction tuning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.114224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90cc9f59-b33a-49a9-8b6d-bfe8d149ab19 · outbound

This paper cites Visual instruction tuning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Visual instruction tuning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.119893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcc4d45e-8e47-4304-92e6-8782866ebf17 · outbound

This paper cites TempCompass: Do Video LLMs Really Understand Videos?.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination TempCompass: Do Video LLMs Really Understand Videos?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.126098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed4a26d4-44b4-4ea9-afd2-a0c074532fe5 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.131502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b294586-5ab2-4bbf-8dc7-ac70814d972a · outbound

This paper cites Compositional chain-of-thought prompting for large multimodal models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Compositional chain-of-thought prompting for large multimodal models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.972918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c2ab1977-10c7-4792-b7f2-9b8883e4bb6b · outbound

This paper cites Kam-cot: Knowledge augmented multimodal chain-of-thoughts reasoning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Kam-cot: Knowledge augmented multimodal chain-of-thoughts reasoning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.954577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5f0b499f-b78a-4530-8bb4-1132459c84e8 · outbound

This paper cites Gpt-4o system card.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Gpt-4o system card

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.937701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d7611116-14db-4f4e-afc9-72a8cfe821ff · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Learning transferable visual models from natural language supervi- sion

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.153643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c425de-b99d-4d42-b227-4a89295de079 · outbound

This paper cites Learning To Retrieve Prompts for In-Context Learning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Learning To Retrieve Prompts for In-Context Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.160409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfbb3fde-d773-4201-84ec-34ab9fc8bfd5 · outbound

This paper cites Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.165361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 651e6ade-92f5-40a6-a53f-b316294644c9 · outbound

This paper cites Cognitive psychology.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Cognitive psychology

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.903238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ad6ad5e7-c6b1-4451-8e09-448e4aee02c1 · outbound

This paper cites Expectation (and attention) in visual cognition.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Expectation (and attention) in visual cognition

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.882580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e6511a7b-8b8f-4f33-848f-39170cec7c3f · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.180971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6fa9169-ed14-42e0-b2a2-0d24ed339044 · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.863860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7fc8af1f-7def-4fa6-95e6-40274a45617e · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination LLaMA: Open and Efficient Foundation Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.191013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47b4dfc1-bf0a-4a5a-b01b-aaf1c93cba43 · outbound

This paper cites Cross modality bias in visual question answering: A causal view with possible worlds vqa.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Cross modality bias in visual question answering: A causal view with possible worlds vqa

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.846308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 21645259-89ca-4f6f-97d2-526a508de09c · outbound

This paper cites Vigc: Visual instruction generation and correction.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Vigc: Visual instruction generation and correction

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.829114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 063d4dfd-0678-4759-ab06-fcb52b1123ae · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.204331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27619d99-79b7-4f59-b1fa-1f32b372487b · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large lan- guage models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Chain-of-thought prompting elicits reasoning in large lan- guage models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.209840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96814179-5438-4fe0-9f7a-c16c0cc22857 · outbound

This paper cites Self-evaluation guided beam search for reasoning.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Self-evaluation guided beam search for reasoning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.797178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 964677b3-b86d-47f7-97e1-7731716164d4 · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Tree of thoughts: Deliberate problem solving with large language models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.221100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2c6989-198b-43ee-987b-7b279199e7ff · outbound

This paper cites Woodpecker: Hallucination Correction for Multimodal Large Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Woodpecker: Hallucination Correction for Multimodal Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.226470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 593b5a7f-0b12-4f86-a585-7fab7a251aef · outbound

This paper cites Contextual object detection with multi- modal large language models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Contextual object detection with multi- modal large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.767096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a76c9d70-7b37-41ec-b452-3fbc1b93f645 · outbound

This paper cites CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.237845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d98664b-cc5f-408c-aca6-3128f8ff547f · outbound

This paper cites LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.251046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f52fecb-9ad2-48ec-b77b-d136b0a4f160 · outbound

This paper cites Automatic Chain of Thought Prompting in Large Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Automatic Chain of Thought Prompting in Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.257211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f2804e1-aa08-4b14-80e7-368bba383291 · outbound

This paper cites Multimodal Chain-of-Thought Reasoning in Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Multimodal Chain-of-Thought Reasoning in Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:45.263587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3f11512-b227-4cc5-875e-26cbd892782d · outbound

This paper cites Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models.Advances in Neu- ral Information Processing Systems, 36:5168–5191, 2023.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models.Advances in Neu- ral Information Processing Systems, 36:5168–5191, 2023

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:45.745985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4de40864-9826-49af-bbc7-6f277bab5103 · outbound

This paper cites Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models

Reference 48

Resolution: malformed identifier; no resolver link, observed 2026-08-12T19:35:45.274312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db9bf6ac-8065-4ad1-8cda-dc6bdc911ad9 · outbound

This paper cites an unresolved cited work.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination Unresolved cited work

Reference 2024

Resolution: parse uncertain; raw_fallback, observed 2026-08-12T19:35:46.152884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 50ea1800-5255-440e-951f-995cfe6c9911 · inbound

Hallucination of Multimodal Large Language Models: A Survey cites this paper.

Hallucination of Multimodal Large Language Models: A Survey Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 220

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:33:33.443213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3b478f3d-7e97-4776-97be-1a2b1dc81a7f · inbound

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey cites this paper.

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 89

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:18:53.749212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7f35f66e-4cbe-463e-a511-e8f97f085ad1 · inbound

MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM cites this paper.

MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T12:33:13.663322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1235f923-a65d-4a8e-b541-feeaed84209a · inbound

Empowering Multimodal LLMs with External Tools: A Comprehensive Survey cites this paper.

Empowering Multimodal LLMs with External Tools: A Comprehensive Survey Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 177

Resolution: unresolved; no resolver link, observed 2026-08-05T20:29:00.846334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e2aae97-76fb-4127-a7c1-4530bfc3e7ae · inbound

MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment cites this paper.

MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T17:10:02.962883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140f773a-c2e3-468a-b8c4-9dc3f4a975b4 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:01.812797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74692ec0-193e-4668-9bc6-eeab11ca3654 · inbound

On Semiotic-Grounded Interpretive Evaluation of Generative Art cites this paper.

On Semiotic-Grounded Interpretive Evaluation of Generative Art Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 91

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:20:52.681366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 86f32005-f045-4120-a6e7-e2ddc4732861 · inbound

Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training cites this paper.

Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:22:23.500754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a612626b-f8e3-49ce-ba22-58413842c0b3 · inbound

CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection cites this paper.

CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-12T06:01:58.407747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4cdebd0-27c0-4833-8107-4148bfc07050 · inbound

VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models cites this paper.

VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-14T04:35:48.425006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.