Paper Citation Record · LEDGER

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models

As of 10 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2507.09185.

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

pith.paper-citation-record.v1
2507.09185 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:08:53.178272Z

measured 48 of 48 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 2026-06-27T00:30:30.315423Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T21:28:59.001963Z

Reference resolution

47 of 47 outbound references displayed

verified exact3
verified fuzzy20
unresolved23
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ce792896-7604-4862-a3b3-ba25ffa6ae82 · outbound

This paper cites Mitigating Copy Bias in In-Context Learning through Neuron Pruning.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Mitigating Copy Bias in In-Context Learning through Neuron Pruning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:46.556612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a0ea3cd-0639-4dd0-9515-e4ca13767ed2 · outbound

This paper cites Impact of Adversarial Training on Robustness and Generalizability of Language Models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Impact of Adversarial Training on Robustness and Generalizability of Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:46.760675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c308160-cdbf-4d06-a528-326557058d50 · outbound

This paper cites will you find these shortcuts? a protocol for evaluating the faithfulness of input salience methods for text classification.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models will you find these shortcuts? a protocol for evaluating the faithfulness of input salience methods for text classification

Reference 3

Resolution: verified exact; doi, observed 2026-08-06T18:08:53.667737Z

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 e4d1d0fd-39cb-4382-be2c-19abc927a1f3 · outbound

This paper cites A large annotated corpus for learning natural language inference.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models A large annotated corpus for learning natural language inference

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:47.117059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 287c8f12-fe0a-448e-af09-d71f990f6620 · outbound

This paper cites Language models are few-shot learners.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Language models are few-shot learners

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:47.312211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b08b28-1c46-4922-89d1-c8643753584e · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:47.595215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92d48bc9-0ce6-43ec-ac55-6ad6394743d7 · outbound

This paper cites Knowledge neurons in pretrained transformers.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Knowledge neurons in pretrained transformers

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:59.050420Z

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 ab949f98-f04e-4b07-a1ac-37cdf2d30622 · outbound

This paper cites BERT : Pre-training of deep bidirectional transformers for language understanding.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models BERT : Pre-training of deep bidirectional transformers for language understanding

Reference 8

Resolution: malformed identifier; no resolver link, observed 2026-08-06T18:08:48.067983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed11ae3-b6db-45c9-bfaf-d0aa2e09223a · outbound

This paper cites Towards interpreting and mitigating shortcut learning behavior of nlu models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Towards interpreting and mitigating shortcut learning behavior of nlu models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:58.869160Z

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 05ee5499-f3bf-45bf-8e5d-a4659d181871 · outbound

This paper cites Shortcut learning of large language models in natural language understanding.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Shortcut learning of large language models in natural language understanding

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:58.699197Z

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 15b76555-9b48-44ec-9493-50936ce25fbb · outbound

This paper cites Data augmentations for improved (large) language model generalization.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Data augmentations for improved (large) language model generalization

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:58.551923Z

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 60c743ff-d8ad-4fec-8816-3cbb64e2596e · outbound

This paper cites Finding dataset shortcuts with grammar induction.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Finding dataset shortcuts with grammar induction

Reference 12

Resolution: verified exact; doi, observed 2026-08-06T18:08:53.390166Z

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 936d3eb0-4268-4a3a-9cc1-8ec7baf137d6 · outbound

This paper cites The Llama 3 Herd of Models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models The Llama 3 Herd of Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:49.610563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7906ead3-6274-40c2-ab06-820e0f5a241d · outbound

This paper cites Universal Neurons in GPT2 Language Models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Universal Neurons in GPT2 Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:49.719227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 607fed81-0374-4936-8982-e7fd410c84d1 · outbound

This paper cites Learning both weights and connections for efficient neural networks.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Learning both weights and connections for efficient neural networks

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:58.396110Z

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 17eb6414-5e56-41e0-bfad-cf87904652b0 · outbound

This paper cites Parameter-efficient fine-tuning for large models: A comprehensive survey.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Parameter-efficient fine-tuning for large models: A comprehensive survey

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:58.254061Z

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 cd130629-8a67-4122-8149-b6a6f493445a · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Measuring Massive Multitask Language Understanding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:49.974170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c14d6e7b-7ad8-4b19-98a8-e8a59b0d9407 · outbound

This paper cites A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:08:54.040105Z

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 4ed815dd-8548-4f4d-abd3-e6be47ac800c · outbound

This paper cites Parameter-efficient transfer learning for nlp.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Parameter-efficient transfer learning for nlp

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:50.134672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a38cf7a-099d-445a-950d-18833bff36ad · outbound

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

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Lora: Low-rank adaptation of large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:50.248379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e9019f0-e940-4b94-ab4b-5147651a9e31 · outbound

This paper cites Regional differences in synaptogenesis in human cerebral cortex.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Regional differences in synaptogenesis in human cerebral cortex

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:58.032415Z

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 9d566abe-f262-4639-981b-a642f3c95bd4 · outbound

This paper cites Mistral 7B.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Mistral 7B

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:50.466917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2410ef2-4c10-4515-bb45-db64a5d56f20 · outbound

This paper cites Llm-blender: Ensembling large language models with pairwise comparison and generative fusion.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Llm-blender: Ensembling large language models with pairwise comparison and generative fusion

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:57.807230Z

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 d818ee0a-80c2-4e34-8cec-4c439ee77836 · outbound

This paper cites Optimal brain damage.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Optimal brain damage

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:50.596350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45f5f05d-8d3e-420e-9022-5e40f69d92e2 · outbound

This paper cites Guiding LLM to fool itself: Automatically manipulating machine reading comprehension shortcut triggers.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Guiding LLM to fool itself: Automatically manipulating machine reading comprehension shortcut triggers

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:57.594790Z

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 bcbd24d9-5498-43a1-93bc-6a387a955066 · outbound

This paper cites Inference-time intervention: Eliciting truthful answers from a language model.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Inference-time intervention: Eliciting truthful answers from a language model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:50.783231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ed70db-28cc-4347-9762-b82c2be1b3e1 · outbound

This paper cites Inference-time intervention: Eliciting truthful answers from a language model.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Inference-time intervention: Eliciting truthful answers from a language model

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:57.272049Z

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 b51a7f26-06a1-4ff7-ad08-8501f136a85c · outbound

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

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Training language models to follow instructions with human feedback

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:50.969984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca62e3a2-19bc-4ae4-addc-31957d7f223d · outbound

This paper cites Extraordinary neoteny of synaptic spines in the human prefrontal cortex.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Extraordinary neoteny of synaptic spines in the human prefrontal cortex

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:56.876017Z

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 8b4e4568-961e-452e-a223-b1310fb4cfd4 · outbound

This paper cites Ponti, Goran Glava s , Olga Majewska, Qianchu Liu, Ivan Vuli' c , and Anna Korhonen.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Ponti, Goran Glava s , Olga Majewska, Qianchu Liu, Ivan Vuli' c , and Anna Korhonen

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:56.610040Z

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 a0f904c3-e001-4ac9-89f7-005352a4b6f5 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Steering llama 2 via contrastive activation addition

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:56.291555Z

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 b0d7b784-825d-423c-a1aa-6dc1206cee39 · outbound

This paper cites Choice of plausible alternatives: An evaluation of commonsense causal reasoning.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Choice of plausible alternatives: An evaluation of commonsense causal reasoning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:55.950787Z

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 e490cb95-c760-4a9e-ba01-e926ce5c28a6 · outbound

This paper cites Recursive deep models for semantic compositionality over a sentiment treebank.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Recursive deep models for semantic compositionality over a sentiment treebank

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:51.823046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 048f5285-6a20-41f5-b0aa-4c98d52c1568 · outbound

This paper cites Confidence regulation neurons in language models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Confidence regulation neurons in language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:55.688521Z

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 27a803dc-f22a-41db-bcd8-1b01be9fb8c6 · outbound

This paper cites A simple and effective pruning approach for large language models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models A simple and effective pruning approach for large language models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:55.374002Z

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 5f819395-516f-4521-8466-d24db40cb6dc · outbound

This paper cites Axiomatic attribution for deep networks.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Axiomatic attribution for deep networks

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:55.195186Z

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 9369243d-5628-45af-8c17-37fa83b78d5e · outbound

This paper cites Large language models can be lazy learners: Analyze shortcuts in in-context learning.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Large language models can be lazy learners: Analyze shortcuts in in-context learning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:52.411960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e1b963f-f261-4b9a-afa8-16ff48047e00 · outbound

This paper cites Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:52.467120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc02c8dd-f83d-40e5-9991-6326928c5706 · outbound

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

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:52.540499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1ea8b9c-1263-42e8-ad2e-8ec6fc606fd1 · outbound

This paper cites Neurons in Large Language Models: Dead, N-gram, Positional.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Neurons in Large Language Models: Dead, N-gram, Positional

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:52.586208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88e172ae-450a-444a-8953-b357dc5da10c · outbound

This paper cites Semantics-adaptive activation intervention for LLM s via dynamic steering vectors.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Semantics-adaptive activation intervention for LLM s via dynamic steering vectors

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:55.019180Z

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 96b621af-4aec-48cf-8596-7ec9ba69c123 · outbound

This paper cites Do LLM s overcome shortcut learning? an evaluation of shortcut challenges in large language models.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Do LLM s overcome shortcut learning? an evaluation of shortcut challenges in large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:54.849594Z

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 3fe1267b-ddf2-492f-aee1-8bdd60a1cdae · outbound

This paper cites Comi: Correct and mitigate shortcut learning behavior in deep neural networks.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Comi: Correct and mitigate shortcut learning behavior in deep neural networks

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:08:54.661693Z

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 e3f263c5-c752-4d45-b4aa-65196a4eab8b · outbound

This paper cites write newline.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models write newline

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:52.905841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dc0a86a-f833-4dc4-831c-745d8216f8be · outbound

This paper cites @esa (Ref.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models @esa (Ref

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:53.008494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 437504c3-4b75-4e4f-836d-4c055bdf9a33 · outbound

This paper cites an unresolved cited work.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Unresolved cited work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:53.054918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 898e68b3-665a-4a7f-9dd4-15478d99828b · outbound

This paper cites an unresolved cited work.

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:53.178272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 454ce4bc-06a9-4a88-ab44-78ccc2474efb · inbound

LLM Parameters for Math Across Languages: Shared or Separate? cites this paper.

LLM Parameters for Math Across Languages: Shared or Separate? Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:28:59.003603Z

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.