Paper Citation Record · LEDGER

Rethinking the Understanding Ability across LLMs through Mutual Information

As of 7 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2505.23790.

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

pith.paper-citation-record.v1
2505.23790 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:21:38.922981Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

46 of 46 outbound references displayed

verified exact2
verified fuzzy15
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 40ae3ade-1642-4115-868d-fea00a1f465e · outbound

This paper cites Comprehensive analysis of falcon 7b: A state-of-the-art generative large language model.

Rethinking the Understanding Ability across LLMs through Mutual Information Comprehensive analysis of falcon 7b: A state-of-the-art generative large language model

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:41.456529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6a78e576-5327-4cb2-abe6-488df5659def · outbound

This paper cites The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?.

Rethinking the Understanding Ability across LLMs through Mutual Information The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:36.988483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9106e1d-62a3-4b82-8988-cae962b89735 · outbound

This paper cites LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements.

Rethinking the Understanding Ability across LLMs through Mutual Information LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:21:39.604011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3f6fa476-e31e-4774-a2e8-819886b163df · outbound

This paper cites LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders.

Rethinking the Understanding Ability across LLMs through Mutual Information LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.128322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fcfedb1-0e40-4391-909c-ceb16cbe8918 · outbound

This paper cites A survey on evaluation of large language models.

Rethinking the Understanding Ability across LLMs through Mutual Information A survey on evaluation of large language models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.190572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38a56e07-de19-4dc8-9905-e9d0e5317836 · outbound

This paper cites Are Decoder-Only Large Language Models the Silver Bullet for Code Search?.

Rethinking the Understanding Ability across LLMs through Mutual Information Are Decoder-Only Large Language Models the Silver Bullet for Code Search?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.221342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a1d7714-e89a-4bf6-b13f-1efc1354c798 · outbound

This paper cites Elements of information theory.

Rethinking the Understanding Ability across LLMs through Mutual Information Elements of information theory

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.231008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7195edb8-cefe-4ea9-8afe-db1e675b84b0 · outbound

This paper cites Testing ai on language comprehension tasks reveals insensitivity to underlying meaning.

Rethinking the Understanding Ability across LLMs through Mutual Information Testing ai on language comprehension tasks reveals insensitivity to underlying meaning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:41.271783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1431d2cb-69ca-4000-912a-c2ce7397c081 · outbound

This paper cites Information theoretic approaches to understanding circuit function.

Rethinking the Understanding Ability across LLMs through Mutual Information Information theoretic approaches to understanding circuit function

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:41.172802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 62695048-f87e-4455-9777-a39f9de492f7 · outbound

This paper cites Dissecting deep learning net- works—visualizing mutual information.

Rethinking the Understanding Ability across LLMs through Mutual Information Dissecting deep learning net- works—visualizing mutual information

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.995100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ca9a8b99-dff6-4dec-a4da-fd9dc3c06b76 · outbound

This paper cites Benchmark performance is a poor measure of generalisable ai reasoning capabili- ties.

Rethinking the Understanding Ability across LLMs through Mutual Information Benchmark performance is a poor measure of generalisable ai reasoning capabili- ties

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.888608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3cfdbff-a0ad-4aaf-8030-68e334d08b2c · outbound

This paper cites Line Goes Up? Inherent Limitations of Benchmarks for Evaluating Large Language Models.

Rethinking the Understanding Ability across LLMs through Mutual Information Line Goes Up? Inherent Limitations of Benchmarks for Evaluating Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.418553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ddb246-41b8-4843-becc-5257c9ac19ed · outbound

This paper cites Entropy and mutual information in models of deep neural networks.

Rethinking the Understanding Ability across LLMs through Mutual Information Entropy and mutual information in models of deep neural networks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.814280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d880a916-9d79-42f3-b1a1-a328e8e97b7d · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Rethinking the Understanding Ability across LLMs through Mutual Information The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.522404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e022b2de-1ae1-4a76-b571-395cff22ac84 · outbound

This paper cites Mistral 7B.

Rethinking the Understanding Ability across LLMs through Mutual Information Mistral 7B

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.571628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01eccbda-e3ec-4408-88cb-3fccdf6fc312 · outbound

This paper cites Mixtral of Experts.

Rethinking the Understanding Ability across LLMs through Mutual Information Mixtral of Experts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.647565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1436fbb-4e1d-4cb9-bd63-77fce7dfc212 · outbound

This paper cites Estimating mutual information.

Rethinking the Understanding Ability across LLMs through Mutual Information Estimating mutual information

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.693088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 435d1d3a-ed96-4219-87f4-8560c2efc2fe · outbound

This paper cites Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks.

Rethinking the Understanding Ability across LLMs through Mutual Information Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.748209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1bd7531-394e-4134-9f27-09c4d8424040 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Rethinking the Understanding Ability across LLMs through Mutual Information RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.754439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97308b57-44ee-49f0-a140-e9f2863670d7 · outbound

This paper cites Maas, Raymond E.

Rethinking the Understanding Ability across LLMs through Mutual Information Maas, Raymond E

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.558307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3b6426b0-8629-4078-ae35-f6755608acf8 · outbound

This paper cites Pointer sentinel mixture models, 2016.

Rethinking the Understanding Ability across LLMs through Mutual Information Pointer sentinel mixture models, 2016

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.783366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71423d7-233f-4198-9510-12f7059353e6 · outbound

This paper cites Named entity recognition.

Rethinking the Understanding Ability across LLMs through Mutual Information Named entity recognition

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.458391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f9e1102c-e821-43f6-8e85-1b5c9af0f37b · outbound

This paper cites MTEB: Massive Text Embedding Benchmark.

Rethinking the Understanding Ability across LLMs through Mutual Information MTEB: Massive Text Embedding Benchmark

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.903247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc06eecf-9a3f-46b6-9f32-99f888155b3d · outbound

This paper cites Using an llm to help with code understanding.

Rethinking the Understanding Ability across LLMs through Mutual Information Using an llm to help with code understanding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.950846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dc8773a-5ab0-4856-8cd1-236e1d3bd123 · outbound

This paper cites Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks.

Rethinking the Understanding Ability across LLMs through Mutual Information Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:37.988237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f1f3cc3-1d2e-411f-a7eb-90764bcb79a5 · outbound

This paper cites How much a galaxy knows about its large-scale envi- ronment?: An information theoretic perspective.

Rethinking the Understanding Ability across LLMs through Mutual Information How much a galaxy knows about its large-scale envi- ronment?: An information theoretic perspective

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.405619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a2259d11-8192-4134-804e-54865e347028 · outbound

This paper cites Reasoning with large language models, a survey.

Rethinking the Understanding Ability across LLMs through Mutual Information Reasoning with large language models, a survey

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.107266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b69c9e23-23ad-4086-8e2b-08df939ec075 · outbound

This paper cites an unresolved cited work.

Rethinking the Understanding Ability across LLMs through Mutual Information Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:21:40.355899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ffc7bcc2-41a5-457c-9601-d4056567c71e · outbound

This paper cites Your Transformer is Secretly Linear.

Rethinking the Understanding Ability across LLMs through Mutual Information Your Transformer is Secretly Linear

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.217837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83f81e3-6a52-4a2a-b36a-d3fdef9fb7ae · outbound

This paper cites LLMs' Understanding of Natural Language Revealed.

Rethinking the Understanding Ability across LLMs through Mutual Information LLMs' Understanding of Natural Language Revealed

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.259171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3d61275-f770-425a-aa89-1c6e4784e764 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

Rethinking the Understanding Ability across LLMs through Mutual Information DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.270536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eef9d627-4be4-4c57-8c0f-1395ff9d3506 · outbound

This paper cites Incremental mutual information: a new method for char- acterizing the strength and dynamics of connections in neuronal circuits.

Rethinking the Understanding Ability across LLMs through Mutual Information Incremental mutual information: a new method for char- acterizing the strength and dynamics of connections in neuronal circuits

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.220380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 52231981-fe1f-4249-afb4-75cda73912ec · outbound

This paper cites Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification.

Rethinking the Understanding Ability across LLMs through Mutual Information Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:21:39.181946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e78e6351-2daa-4618-9c63-9105da7e6fec · outbound

This paper cites Layer by Layer: Uncovering Hidden Representations in Language Models.

Rethinking the Understanding Ability across LLMs through Mutual Information Layer by Layer: Uncovering Hidden Representations in Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.302301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63d0af12-cd1d-4ea8-b9b8-f766ec1e74bf · outbound

This paper cites Table meets llm: Can large language models understand structured table data? a benchmark and empirical study.

Rethinking the Understanding Ability across LLMs through Mutual Information Table meets llm: Can large language models understand structured table data? a benchmark and empirical study

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:40.118233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9238ed69-5f52-42e1-a0bf-fe53401898c6 · outbound

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

Rethinking the Understanding Ability across LLMs through Mutual Information Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.440373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30c59398-86b8-435c-8a78-3248cad0ef39 · outbound

This paper cites Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information.

Rethinking the Understanding Ability across LLMs through Mutual Information Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.587264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ae040c-f636-4071-9e33-1253a19d11ee · outbound

This paper cites Fact or fiction: Verifying scientific claims.

Rethinking the Understanding Ability across LLMs through Mutual Information Fact or fiction: Verifying scientific claims

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:39.998253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2664d794-d8a2-4f21-9e18-de45b87558bd · outbound

This paper cites an unresolved cited work.

Rethinking the Understanding Ability across LLMs through Mutual Information Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.694975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baaae28c-3b38-438e-82b1-6b684fce121d · outbound

This paper cites Mutual information as a tool for identifying phase transitions in dynamical complex systems with limited data.

Rethinking the Understanding Ability across LLMs through Mutual Information Mutual information as a tool for identifying phase transitions in dynamical complex systems with limited data

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:39.878363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c80635c-329f-41b6-9230-bfb6d25924c0 · outbound

This paper cites Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders.

Rethinking the Understanding Ability across LLMs through Mutual Information Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.790530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f66ef4-4188-4b8e-9e8d-d83f8ea50dd5 · outbound

This paper cites Open, Closed, or Small Language Models for Text Classification?.

Rethinking the Understanding Ability across LLMs through Mutual Information Open, Closed, or Small Language Models for Text Classification?

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.799618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b00469a-94eb-41f4-85f0-20990a9834f4 · outbound

This paper cites When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method.

Rethinking the Understanding Ability across LLMs through Mutual Information When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.805940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 280e8548-8ff4-45fa-a5f1-3234c8235c5d · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Rethinking the Understanding Ability across LLMs through Mutual Information OPT: Open Pre-trained Transformer Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.828737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c364fd46-442d-458b-8678-1557effd9e99 · outbound

This paper cites Character-level Convolutional Networks for Text Classification.

Rethinking the Understanding Ability across LLMs through Mutual Information Character-level Convolutional Networks for Text Classification

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:38.886068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ee31aa-5ada-4d70-b203-cd7b4dc31162 · outbound

This paper cites Character-level convolutional networks for text classification.

Rethinking the Understanding Ability across LLMs through Mutual Information Character-level convolutional networks for text classification

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:21:39.740791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.