Pith. sign in

Paper Citation Record · LEDGER

Enhancing Cross-task Transfer of Large Language Models via Activation Steering

As of 8 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 2 inbound Pith citation observations for arXiv:2507.13236.

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

pith.paper-citation-record.v1
2507.13236 v1

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:31:51.435774Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-04T22:50:36.506757Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T23:00:11.079370Z

Reference resolution

57 of 57 outbound references displayed

  • verified exact4
  • verified fuzzy35
  • unresolved18
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ad7d969a-447c-43de-a8df-40c978f7e904 · outbound

This paper cites A Survey of Large Language Models.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering A Survey of Large Language Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.262245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.262245Z digest=sha256:a952b26797d784e50bb9e979ac0edbcecde8563a940c46195066db3dd8d90997

Observation f8ef13bc-c109-4201-a7ad-c07d32cb32b0 · outbound

This paper cites Learning to reason with llms, 2024.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Learning to reason with llms, 2024

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.265941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.265941Z digest=sha256:27edc806925a1294abf19d1c97d73ecd5a831f07c55c8cfeb5ef52566a2de17a

Observation 031d6bd3-bb6c-42b4-b190-11a6a61b809b · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.268771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.268771Z digest=sha256:d823669d52885de06ebb598f4f218ec5cf7a5b856b9dc90366738c7660fced3b

Observation 1c889018-4fdd-4a94-8d83-75041490a769 · outbound

This paper cites The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:31:51.720451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.271974Z digest=sha256:184c787fe121dabef27e99292be2b75290a5fc591bb954ab3d229874611bfcaf

Observation bc8937aa-072e-4e8a-9480-01c58ef79586 · outbound

This paper cites A comprehensive survey on transfer learning.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering A comprehensive survey on transfer learning

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.105857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.275616Z digest=sha256:289327f785e016a1e16a3ae587ea51545946fd0c64a144384b177174439173ba

Observation 4f2cf031-5ea0-4e62-a913-b4f538ec0d53 · outbound

This paper cites Franke, Ivo Rapant, Fabio Ferreira, and Frank Hutter.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Franke, Ivo Rapant, Fabio Ferreira, and Frank Hutter

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.094229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.279255Z digest=sha256:816f1e3c4f0ed3c9fe78ee2b958fdc10724b36230a03b0223316d89013c019f5

Observation 2ab96f55-b21c-4c52-a75b-44aa985d7496 · outbound

This paper cites A transfer learning framework for weak to strong generalization.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering A transfer learning framework for weak to strong generalization

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.085545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.282621Z digest=sha256:ac3759232ad45d7955f14841a734f9a6e3c93f09ff39e7a6bfd8b31a81cf2ec1

Observation 58ff401f-c590-4162-bfbb-bcbbc735ea37 · outbound

This paper cites Spot: Better frozen model adaptation through soft prompt transfer.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Spot: Better frozen model adaptation through soft prompt transfer

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.076501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.285607Z digest=sha256:7605bdbac81af237731cad1b90cfe4be0dc448434d2999f327e37102e075ee63

Observation d92c0c95-8cad-4a57-9b13-92e4019e65f7 · outbound

This paper cites Learning to transfer prompts for text generation.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Learning to transfer prompts for text generation

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.068054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.288330Z digest=sha256:118c415bdd6cf41dbad86260a58b043a4fc176c3c92d4071a5f258f22e86aebe

Observation b79cccf2-01b0-4056-800b-2ce63c25477b · outbound

This paper cites Hyperlora: Efficient cross-task generalization via constrained low-rank adapters genera- tion.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Hyperlora: Efficient cross-task generalization via constrained low-rank adapters genera- tion

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.059537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.291326Z digest=sha256:1fd0b8a27cc6565f095808cc697015c0b00ad3aaa1e16ead944cb4b4dbf6dc5a

Observation bead3e33-8163-4865-a5f1-4592a0e51168 · outbound

This paper cites Soft Language Prompts for Language Transfer.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Soft Language Prompts for Language Transfer

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:31:51.707143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.294213Z digest=sha256:277682645031b92d9e087a06c5127ad3f3961386a2a14c8b74846e6db6e3c893

Observation 590724b8-60a8-4e15-8119-edc245abb9e3 · outbound

This paper cites Multilingual llms are better cross-lingual in-context learners with alignment.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Multilingual llms are better cross-lingual in-context learners with alignment

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.050635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.297846Z digest=sha256:74e1e2b43067ae6c57a06130f167d775260066e64012575a7eeac74f3aa17237

Observation ba7e742b-3bba-4bff-b92c-85eb18fb6f3d · outbound

This paper cites Llms are few-shot in-context low- resource language learners.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Llms are few-shot in-context low- resource language learners

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.041185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.300740Z digest=sha256:600fe45b621f8d95be16d05c53653f6d831bae5a331d0bb8da55626ca45d15d9

Observation edf91df9-1a94-4e1b-acaa-7f3105c0d0c0 · outbound

This paper cites From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.303510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.303510Z digest=sha256:32c76cb2bd69a049a98099e25516cd4f0be46adcfb452799451912889d65e7b6

Observation 7c8354be-d7ce-4636-97c5-50910f56d805 · outbound

This paper cites Language models can exploit cross-task in-context learning for data-scarce novel tasks.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Language models can exploit cross-task in-context learning for data-scarce novel tasks

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.031577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.306634Z digest=sha256:e8ccf0277d7563a26f7035c6f8fd555426d80e3c86a8754be1166242b39b4c9a

Observation e076dc3d-105a-4d16-b1be-b985f9c09e93 · outbound

This paper cites Diverse demonstrations improve in-context compositional generalization.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Diverse demonstrations improve in-context compositional generalization

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.012889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.312145Z digest=sha256:cdf112163dcb84bd111e811777bd39e134b5623214446b999fc78c11aeda7e4c

Observation 529dcaa7-1447-490d-8102-2605ec44a941 · outbound

This paper cites Complementary explanations for effective in-context learning.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Complementary explanations for effective in-context learning

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.004571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.314926Z digest=sha256:f269862b6f17df4290594e743e18802d3cdcaf3eb52f3d90129efd8e09985bd5

Observation ccf39bf6-c786-4e8a-a1fd-fa54d89fdaf8 · outbound

This paper cites Smith, Daniel Khashabi, and Hannaneh Hajishirzi.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Smith, Daniel Khashabi, and Hannaneh Hajishirzi

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.995813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.318077Z digest=sha256:acbdd7f5606fcc0554a6f0dbe062d2f436cb0e4dd7883439c743c1462ebaaeaa

Observation 1535e9be-82c3-462f-a58d-a11c2447f003 · outbound

This paper cites Cross-task gen- eralization via natural language crowdsourcing instructions.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Cross-task gen- eralization via natural language crowdsourcing instructions

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.986970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.321129Z digest=sha256:39c0d77f35fd3a38e691e0d72ba81007dab1622b28bbe015f7829c2a04894dbe

Observation edc733f1-7186-491a-b64f-330b3ea50fe9 · outbound

This paper cites Continuous Transfer Learning with Label-informed Distribution Alignment.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Continuous Transfer Learning with Label-informed Distribution Alignment

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:31:51.684545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.323918Z digest=sha256:20c7e35ab89c759a29a92880e13702e52eec02040581e47115fd9a5716fdfd89

Observation 9b97903a-cb12-40ee-bca3-f46440c6fea6 · outbound

This paper cites Continual transfer learning for cross-domain click-through rate prediction at taobao.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Continual transfer learning for cross-domain click-through rate prediction at taobao

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.978094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.327052Z digest=sha256:0497fcdf7cfdce96927962200fa6958ef2ea0b7a8af3bb013b1a84ae2fda5ca5

Observation 25a1fa2c-81a2-4ebf-9b24-b7bbb3239346 · outbound

This paper cites Aligning large language models with human preferences through representation engineering.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Aligning large language models with human preferences through representation engineering

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.969069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.329902Z digest=sha256:1cb781ec8e100c41b53b574ccc105f57aeb8949f6df22213c1833da0251101ae

Observation 773ecd0f-471b-42a5-b870-0e280b5deeef · outbound

This paper cites Personalized steering of large language models: Versatile steering vectors through bi-directional preference optimization.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Personalized steering of large language models: Versatile steering vectors through bi-directional preference optimization

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.959980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.332600Z digest=sha256:6c83c4629b2612f95c10cf4594ce6de282640ad44924f40657d5d3f55ac3090c

Observation 05ba3504-7363-4b17-9611-a6b48396eefb · outbound

This paper cites Improving instruction-following in language models through activation steering.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Improving instruction-following in language models through activation steering

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.951432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.335298Z digest=sha256:e0b144301c895e0af68d823ced375c3cf8bd7fd8103068c196968f937803b637

Observation 553aaef3-b5ae-4bdd-9186-13617e60a9a8 · outbound

This paper cites Viégas, Hanspeter Pfister, and Martin Wattenberg.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Viégas, Hanspeter Pfister, and Martin Wattenberg

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.942136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.338336Z digest=sha256:64ce85b17698d27910776a95237b5e629802713b4a9dbf0851bb8aa5240308db

Observation d40a876b-356d-40b6-b314-7ca17f34d17f · outbound

This paper cites Refusal in language models is mediated by a single direction.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Refusal in language models is mediated by a single direction

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.933270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.341279Z digest=sha256:030d41d6fb5e1bad3317ae4cdc7333cefab69ad0470ca7615d7184a75cd08f97

Observation 9e806eb7-a60f-4f48-86ba-80ae4bc621d2 · outbound

This paper cites an unresolved cited work.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Unresolved cited work

Reference 28

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:31:51.924231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.344227Z digest=sha256:29f318b93653876f6b8de4cca3bd16a5e7be3f5e548f08e6c85d16a4f22114bd

Observation 08935846-38cc-466b-810a-023bbe453fa6 · outbound

This paper cites Improving reasoning performance in large language models via representation engineering.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Improving reasoning performance in large language models via representation engineering

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.914795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.347323Z digest=sha256:96c5dffe7b70429be7b04528e68c85efbd67e8b2f003433b3c4b0b02e1c9e61d

Observation 34ec79ad-94b0-41b6-8ca0-aacc6ccaf376 · outbound

This paper cites Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.350436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.350436Z digest=sha256:3df5f3c2e9a17e11a4cc6eb67f904993185b1c6cec4b4f187384998625c7c434

Observation 2289cd90-051a-4449-beaa-2e660cdca594 · outbound

This paper cites Neural networks and physical systems with emergent collective computational abilities.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Neural networks and physical systems with emergent collective computational abilities

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.905212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.353672Z digest=sha256:8859d4494c17e467a15f06bcaa0a03438df941a8263632325ecfa6d214890962

Observation 02ead569-cc77-430f-93f4-9f0cb5e42da5 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.356477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.356477Z digest=sha256:b95abdc740f5b71e8665e8d388b02857dc0e9c5aae4f6c85471c2bba98ea2510

Observation 95c95e5a-aa9c-4da0-ad06-8662eaf8d761 · outbound

This paper cites DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.360922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.360922Z digest=sha256:efbdcb9e1648eeb8fc0d49b29311e95d472406aa83ef8cecb847b1ab4e9ca8f7

Observation c37954db-bb84-41ed-bb7a-165eb851ea61 · outbound

This paper cites Diff-erank: A novel rank-based metric for evaluating large language models.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Diff-erank: A novel rank-based metric for evaluating large language models

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.896086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.364144Z digest=sha256:017ad3cfdf8c3808d248379e8512f2ead8cad45d51549b9228e8e4d82dba0e8f

Observation c26df17d-df75-4dfd-9e5b-f09f6607941d · outbound

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

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Layer by Layer: Uncovering Hidden Representations in Language Models

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.367025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.367025Z digest=sha256:80cf959d2461cd44ea894b4d81cb794633896b795b5fc72861eab4c0cb945375

Observation 1c3b7d61-7009-4ef7-ab59-a66c3c922c11 · outbound

This paper cites Visualizing data using t-sne.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Visualizing data using t-sne

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.887299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.370673Z digest=sha256:3d52dbdd44ac1a178094ebb5b4495351006afd92f7bd6f2ab4bd9de1eae45b07

Observation 9abc58f8-cb77-4fd7-9fd7-408b01f4b831 · outbound

This paper cites M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.373334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.373334Z digest=sha256:c3e3799ebd0006901930598b7c0d1dad8a25ee19eff114481a7b9599a41128d0

Observation e80f85c6-8dea-45eb-a626-5d9ebb80fb4e · outbound

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

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.376340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.376340Z digest=sha256:018d6857fd1d86fe4c7d3b8c17a8c41a0a5e88dff9d588975edd855ad554e4fa

Observation 216415f6-121d-432c-a69f-3c7ae6978a2b · outbound

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

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Character-level convolutional networks for text classification

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.878154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.379188Z digest=sha256:948e3f3760b115c31975de024e7a44b2f1f8011928e4a9b2790b3662e55b26cf

Observation 8a9f2eee-13e7-4526-ab16-63d8bd302297 · outbound

This paper cites Boolq: Exploring the surprising difficulty of natural yes/no questions.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Boolq: Exploring the surprising difficulty of natural yes/no questions

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.868925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.382065Z digest=sha256:3c3e605d6329e1987006a12114e278ef9c90da5458c36dc6eed4bcd1d69293f0

Observation c31d3868-791d-4ad5-ad27-68007faf20b9 · outbound

This paper cites Commonsenseqa: A question answering challenge targeting commonsense knowledge.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Commonsenseqa: A question answering challenge targeting commonsense knowledge

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.859701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.385194Z digest=sha256:14476a2db2da1cf6b030f1ebe365280a00fb1313a9d4f4a714b97b446ad29273

Observation ff936026-689f-4a3a-90ef-c80f64f8b816 · outbound

This paper cites an unresolved cited work.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:31:51.849350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.388462Z digest=sha256:62afcb8d5705724cd4f5f0e77059ed92f0736a15f9fdec0480bc658e92dfd251

Observation ca1e765b-4862-4ead-9bfb-20c73f494463 · outbound

This paper cites Natural Language Understanding with the Quora Question Pairs Dataset.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Natural Language Understanding with the Quora Question Pairs Dataset

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.391018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.391018Z digest=sha256:5e182df5e2b45a476ddca66ae39a1c93a6e727f08815761e29113fa919e9c824

Observation cf9b71f6-f7fa-4844-91c6-a24ff7b2b036 · outbound

This paper cites Manning, Andrew Y.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Manning, Andrew Y

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.840469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.394198Z digest=sha256:dd6d06c36b4ca409889c70296213233fa71a0dfdb839033373b16c9440c743e2

Observation 0a125005-5d55-45fd-82f8-b72e8c3076da · outbound

This paper cites Korhonen, Jyrki Wallenius, and Pyry Takala.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Korhonen, Jyrki Wallenius, and Pyry Takala

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.831604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.397120Z digest=sha256:29b9f99c93a49197a8a55edd58d5207c9d9c7264f3ef9d9bec2fdbbef8507a83

Observation 231e176a-3668-45cd-9a8e-54b35e340b0c · outbound

This paper cites Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.821950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.399921Z digest=sha256:63264528039ad51773fc684cdde38b9530cd941315e615e97508e4aa77c220bb

Observation 0b81fe62-47c0-4732-930e-1a10cb01d9b4 · outbound

This paper cites The sciqa scientific question answering benchmark for scholarly knowledge.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering The sciqa scientific question answering benchmark for scholarly knowledge

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.811140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.402692Z digest=sha256:610f5f8e52b3c06eb770076fad8e63324ed7cc68d21feee2593d88db2a6bb63f

Observation c0062076-2557-4794-9063-f86ed1e4c47c · outbound

This paper cites SocialIQA: Commonsense Reasoning about Social Interactions.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering SocialIQA: Commonsense Reasoning about Social Interactions

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.405453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.405453Z digest=sha256:0aaec615638c926726e1295f314c9162aaef9d3d475a2c2f632b36dab987aba1

Observation 9fc0daa6-1dcb-423d-9988-4fbb5ea0c895 · outbound

This paper cites an unresolved cited work.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:31:51.801432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.408532Z digest=sha256:01db67031555741ffbe86fbba2d7f6f441b215a1a2207ab81cd21cb1675c7d3b

Observation a1dbe7e3-f7c1-4bc5-baf7-bb7f26486dd6 · outbound

This paper cites What makes good in-context examples for gpt-3? In DeeLIO@ACL, pages 100–114.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering What makes good in-context examples for gpt-3? In DeeLIO@ACL, pages 100–114

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:52.022127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.411325Z digest=sha256:3ffa33dcc7f96a8481c64461363da79dfb840ee16c86950c30f8eddffdfaef18

Observation 62473336-19ad-472d-aa3c-ffcdf66e4016 · outbound

This paper cites Compositional ex- emplars for in-context learning.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Compositional ex- emplars for in-context learning

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.791766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.414134Z digest=sha256:b91b23a120d0ccedda5291678faa9438a557b57effa0c5eb0d9c165f52ad480f

Observation 1e3adff8-8970-45df-8a69-f87252bd5d7e · outbound

This paper cites The Llama 3 Herd of Models.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering The Llama 3 Herd of Models

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.417648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.417648Z digest=sha256:10a366107e45ac47ec83d13d79cb00b7ea90c6e9f7e76ddbdbc06145501484a5

Observation 31329a11-8bd3-4e0b-9220-281d8cfe3fcc · outbound

This paper cites Smith, and Tao Yu.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Smith, and Tao Yu

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.782453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.420552Z digest=sha256:340de3d2f6d8d3ef515cc987f621f0b2abc8a4626175106ca0d71c1560727bca

Observation 7955fc88-f1b4-4203-b3e1-78b9cb5080b7 · outbound

This paper cites IDEAL: influence-driven selective annotations empower in-context learners in large language models.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering IDEAL: influence-driven selective annotations empower in-context learners in large language models

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.773105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.423376Z digest=sha256:39296731762ea69272c7e96f905b17ff118e19be34e07cb72fdd352f3cbd41a1

Observation 89333fe4-4793-42b2-a49e-dec3c5725038 · outbound

This paper cites Let’s verify step by step.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Let’s verify step by step

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.426363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.426363Z digest=sha256:9a4894281aab368c118d734fc165764ab44052ce0b1cd5a9036b07151669ad10

Observation be2d9879-5170-4cac-b962-8690c68c52c8 · outbound

This paper cites an unresolved cited work.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering Unresolved cited work

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-06T16:31:51.429344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:31:51.429344Z digest=sha256:a531b556178c8132800cdfd4e396214dde2b93305d2c20c4e96d613f5329652c

Observation 84920ed7-6f32-49a0-8e32-9d5ab27cfd14 · outbound

This paper cites A.", "B.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering A.", "B

Reference 57

Resolution
verified exact
raw_fallback, observed 2026-08-06T16:31:51.585028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.432097Z digest=sha256:c7eade39ac580af0d4d7d61b495da59bb09614f62da9ad643b0248131060c72f

Observation bb86fc6f-8987-4d2f-ad23-24744856cb91 · outbound

This paper cites A.", "B.

Enhancing Cross-task Transfer of Large Language Models via Activation Steering A.", "B

Reference 2017

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:31:51.749823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:31:51.435774Z digest=sha256:ac9eb9ef1806d07921658afc3a89f066afbc6c0858840da9ab315ab1cfbdf2d2

Pith citing papers

Observation 896af639-0c81-4d08-bd33-657dd022c36b · inbound

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation cites this paper.

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation Enhancing Cross-task Transfer of Large Language Models via Activation Steering

Reference 57

Resolution
verified exact
arxiv_id, observed 2026-05-21T11:24:08.706196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-21T11:21:30.867480Z digest=sha256:20b6c44cc410d540a7431066eb867bcea724b8d57fe787e8d7208e6a9e5233a7

Observation 364fe378-d995-4e23-a4c8-5567046cfffe · inbound

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure cites this paper.

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure Enhancing Cross-task Transfer of Large Language Models via Activation Steering

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-07-04T23:00:11.081448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-07-04T22:50:36.506757Z digest=sha256:49d152b25d0bc6f72e6f7cd892bd817350d414c5c6456dd65372df69ae9c60aa