Paper Citation Record · LEDGER

Activation Reward Models for Few-Shot Model Alignment

As of 14 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 3 inbound Pith citation observations for arXiv:2507.01368.

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

pith.paper-citation-record.v1
2507.01368 v1

Coverage vector

measured 75 of 75 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:02:42.537188Z

measured 78 of 78 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T02:39:02.891861Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T13:46:04.570352Z

Reference resolution

75 of 75 outbound references displayed

verified exact0
verified fuzzy26
unresolved49
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a309e831-ad2e-4be8-83ef-60ed9188627e · outbound

This paper cites an unresolved cited work.

Activation Reward Models for Few-Shot Model Alignment Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.321263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3392bfb3-0a1b-4fa3-b2c9-0efd1d22b87f · outbound

This paper cites Qwen2.5-VL Technical Report.

Activation Reward Models for Few-Shot Model Alignment Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.325145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39bdd43-c782-4440-85ce-e37b73592ede · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Activation Reward Models for Few-Shot Model Alignment Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.331317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca3027ac-b74b-4c0e-b83f-5a15eface521 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Activation Reward Models for Few-Shot Model Alignment Constitutional AI: Harmlessness from AI Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.337121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71de3fff-e5fe-4a2f-8a1e-0c330a8d5a01 · outbound

This paper cites Capturing individual human preferences with reward features.

Activation Reward Models for Few-Shot Model Alignment Capturing individual human preferences with reward features

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.339704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e72bd98-4df8-4b46-ab47-2f018686a0d8 · outbound

This paper cites Network dissection: Quantify- ing interpretability of deep visual representations.

Activation Reward Models for Few-Shot Model Alignment Network dissection: Quantify- ing interpretability of deep visual representations

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.378656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 61cdfbcf-9caf-459b-81d2-7543ce242d59 · outbound

This paper cites Understanding the role of individual units in a deep neural network.

Activation Reward Models for Few-Shot Model Alignment Understanding the role of individual units in a deep neural network

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.370334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 53587fdb-b7bb-48fe-99fd-bbac1ee0e9d9 · outbound

This paper cites Language Models are Few-Shot Learners.

Activation Reward Models for Few-Shot Model Alignment Language Models are Few-Shot Learners

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.348325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73ebb749-b745-4825-9bd6-38f9b129794b · outbound

This paper cites RRHF-V: Ranking responses to mitigate hallucinations in multimodal large language models with human feedback.

Activation Reward Models for Few-Shot Model Alignment RRHF-V: Ranking responses to mitigate hallucinations in multimodal large language models with human feedback

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.361377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a7db32e6-3734-400e-ae30-4dc63aedd773 · outbound

This paper cites Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, Vlad Mikulik, Sam Bowman, Jan Leike, Jared Kaplan, and Ethan Perez.

Activation Reward Models for Few-Shot Model Alignment Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, Vlad Mikulik, Sam Bowman, Jan Leike, Jared Kaplan, and Ethan Perez

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.344698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bcab6f08-6cb1-457a-992b-c32bdb4344f6 · outbound

This paper cites Christiano, Jan Leike, Tom B.

Activation Reward Models for Few-Shot Model Alignment Christiano, Jan Leike, Tom B

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.336451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 333f3104-8309-43ff-a71a-fa32a444418a · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Activation Reward Models for Few-Shot Model Alignment Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.362383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b8325f5-f3fe-49db-925f-63231a3714a4 · outbound

This paper cites Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking.

Activation Reward Models for Few-Shot Model Alignment Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.365297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd0d2183-911c-4a10-84e4-5364a54d0916 · outbound

This paper cites Paint by Word.

Activation Reward Models for Few-Shot Model Alignment Paint by Word

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.368595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565ec317-f552-4704-8525-3be5fb04fa51 · outbound

This paper cites A Survey on LLM-as-a-Judge.

Activation Reward Models for Few-Shot Model Alignment A Survey on LLM-as-a-Judge

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.371326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b27f7cc-25e1-485c-9580-29ab4868c157 · outbound

This paper cites M-RewardBench: Evaluating Reward Models in Multilingual Settings.

Activation Reward Models for Few-Shot Model Alignment M-RewardBench: Evaluating Reward Models in Multilingual Settings

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.374334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 701e53e9-6d25-4896-916e-b67d26311382 · outbound

This paper cites In-context learning creates task vectors.

Activation Reward Models for Few-Shot Model Alignment In-context learning creates task vectors

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.327878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2b2b4cff-a11b-420f-ad15-f45d39767669 · outbound

This paper cites In-Context Learning Creates Task Vectors.

Activation Reward Models for Few-Shot Model Alignment In-Context Learning Creates Task Vectors

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.379822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ad2182-a253-43d3-9764-a0c2b1c06f15 · outbound

This paper cites Inspecting and Editing Knowledge Representations in Language Models.

Activation Reward Models for Few-Shot Model Alignment Inspecting and Editing Knowledge Representations in Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.382687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bff11584-e388-4db1-b95c-74ee3e411e88 · outbound

This paper cites Finding visual task vectors.

Activation Reward Models for Few-Shot Model Alignment Finding visual task vectors

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.318883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 26c76699-badc-4c7e-861a-fd81a78130c5 · outbound

This paper cites SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality.

Activation Reward Models for Few-Shot Model Alignment SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.387975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8fe77af-5b37-4b9d-ac1d-607631c37add · outbound

This paper cites Multimodal task vectors enable many-shot multimodal in-context learning.

Activation Reward Models for Few-Shot Model Alignment Multimodal task vectors enable many-shot multimodal in-context learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.309709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 739cb215-0073-4d93-91f7-2a70c9221e3d · outbound

This paper cites Multimodal task vectors enable many-shot multimodal in-context learning.

Activation Reward Models for Few-Shot Model Alignment Multimodal task vectors enable many-shot multimodal in-context learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.300705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ca3a6e68-0545-4c7a-aadb-9fb082c0ee22 · outbound

This paper cites RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment.

Activation Reward Models for Few-Shot Model Alignment RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.396463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8acdb000-0686-4932-9d12-8726a2b6d43c · outbound

This paper cites Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes.

Activation Reward Models for Few-Shot Model Alignment Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.399277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5529c393-9ff4-4b69-8aad-fd628fabf51a · outbound

This paper cites RewardBench: Evaluating Reward Models for Language Modeling.

Activation Reward Models for Few-Shot Model Alignment RewardBench: Evaluating Reward Models for Language Modeling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.402165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a064690-906b-4d33-b571-b637800c65ef · outbound

This paper cites RLAIF vs.

Activation Reward Models for Few-Shot Model Alignment RLAIF vs

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.291393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1bd11883-f8cd-44a9-b664-ddd46ee6c5ff · outbound

This paper cites RLAIF vs.

Activation Reward Models for Few-Shot Model Alignment RLAIF vs

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.281451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 301eebe0-a8d2-4d91-9e22-d502c04e8352 · outbound

This paper cites The power of scale for parameter-efficient prompt tuning.

Activation Reward Models for Few-Shot Model Alignment The power of scale for parameter-efficient prompt tuning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.272260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d5696a21-e77d-48dd-87c1-d6158f0f5657 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Activation Reward Models for Few-Shot Model Alignment LLaVA-OneVision: Easy Visual Task Transfer

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.413245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ac81866-ea23-4e7a-89f0-c1a62e6a1509 · outbound

This paper cites BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models.

Activation Reward Models for Few-Shot Model Alignment BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.416301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0495770b-eb30-4685-bb38-1008d01ebe57 · outbound

This paper cites Evaluating text-to-visual generation with image-to-text generation.

Activation Reward Models for Few-Shot Model Alignment Evaluating text-to-visual generation with image-to-text generation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.256118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 82779433-6465-4df6-9e46-967589565a75 · outbound

This paper cites Inform: Mitigating reward hacking in rlhf via information-theoretic reward modeling.

Activation Reward Models for Few-Shot Model Alignment Inform: Mitigating reward hacking in rlhf via information-theoretic reward modeling

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.247216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e87e8d74-2e2e-4461-b28c-1e519c258d34 · outbound

This paper cites Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features.

Activation Reward Models for Few-Shot Model Alignment Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.424201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2295d038-75a9-4a7b-92da-5174726ff034 · outbound

This paper cites Rule Based Rewards for Language Model Safety.

Activation Reward Models for Few-Shot Model Alignment Rule Based Rewards for Language Model Safety

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.427164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f932738d-68f2-4a43-9acd-b74640b2bcbf · outbound

This paper cites In-context Learning and Induction Heads.

Activation Reward Models for Few-Shot Model Alignment In-context Learning and Induction Heads

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.429971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9de138df-d363-4716-a9cf-d5e70f13e740 · outbound

This paper cites GPT-4 Technical Report.

Activation Reward Models for Few-Shot Model Alignment GPT-4 Technical Report

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.432668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e53c4cd-a86c-401b-a243-ea10fb95f939 · outbound

This paper cites an unresolved cited work.

Activation Reward Models for Few-Shot Model Alignment Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:02:43.238094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ed740f6a-768d-440b-ae61-43cb915c2319 · outbound

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

Activation Reward Models for Few-Shot Model Alignment Training language models to follow instructions with human feedback

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.229102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 09a7c555-8945-4616-ac78-ffc005f697fa · outbound

This paper cites an unresolved cited work.

Activation Reward Models for Few-Shot Model Alignment Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:02:43.219895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 18c8f537-ed32-4557-a495-86e6bfb803a1 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Activation Reward Models for Few-Shot Model Alignment Steering Llama 2 via Contrastive Activation Addition

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.443531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ef9ecfa-3019-442a-90d9-88d37689425d · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.

Activation Reward Models for Few-Shot Model Alignment Pytorch: An imperative style, high-performance deep learning library

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.446511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdc8313f-0b58-48f9-b918-8a89e203f6ba · outbound

This paper cites Red Teaming Language Models with Language Models.

Activation Reward Models for Few-Shot Model Alignment Red Teaming Language Models with Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.449385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89618b88-420f-45bd-ae5d-8471c85695b0 · outbound

This paper cites Improving language understanding by generative pre-training.

Activation Reward Models for Few-Shot Model Alignment Improving language understanding by generative pre-training

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.452328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0234c10-4552-46d9-a723-ca951d5ca19e · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Activation Reward Models for Few-Shot Model Alignment Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.455001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b59a616-ab3d-40e1-a961-41b0ddcf8921 · outbound

This paper cites GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation.

Activation Reward Models for Few-Shot Model Alignment GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.457877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a76f31-3f9e-4e7a-923b-1454c5381435 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Activation Reward Models for Few-Shot Model Alignment Proximal Policy Optimization Algorithms

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.461296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68bbd057-2773-4fa5-a82f-ded588030d21 · outbound

This paper cites Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations.

Activation Reward Models for Few-Shot Model Alignment Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.463921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6b977d1-c958-4b0e-8354-29a257170a05 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Activation Reward Models for Few-Shot Model Alignment DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.466647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 416fede6-7ea0-435b-b28f-6c9561e43e39 · outbound

This paper cites FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users.

Activation Reward Models for Few-Shot Model Alignment FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.469412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01895fb7-6d99-4260-ad20-7e6d22c9fcd4 · outbound

This paper cites Alpaca: A strong, replicable instruction- following model.

Activation Reward Models for Few-Shot Model Alignment Alpaca: A strong, replicable instruction- following model

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.199194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6a231fd1-79dc-4ccd-9ef3-66cb51d24458 · outbound

This paper cites Learning to summarize with human feedback.

Activation Reward Models for Few-Shot Model Alignment Learning to summarize with human feedback

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.475288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01348201-5f79-4333-a21a-8e69d5d86b58 · outbound

This paper cites Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, Paul Christiano, Jan Leike, and Others.

Activation Reward Models for Few-Shot Model Alignment Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, Paul Christiano, Jan Leike, and Others

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.183491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7597d84e-84c7-4f0c-ae61-22ea44d0e9ff · outbound

This paper cites Extracting latent steering vectors from pretrained language models.

Activation Reward Models for Few-Shot Model Alignment Extracting latent steering vectors from pretrained language models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.173972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6c308a2a-af65-4032-94a0-27c9dc16d7ee · outbound

This paper cites Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence.

Activation Reward Models for Few-Shot Model Alignment Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.483528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d87fff3e-fc59-4c55-8b05-953b8182f488 · outbound

This paper cites Li, Arnab Sen Sharma, Aaron Mueller, Byron C.

Activation Reward Models for Few-Shot Model Alignment Li, Arnab Sen Sharma, Aaron Mueller, Byron C

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.163979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5b0d810c-d934-4b46-a0ab-e1a0b4d32077 · outbound

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

Activation Reward Models for Few-Shot Model Alignment LLaMA: Open and Efficient Foundation Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.488755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d292f8cf-a3bb-4424-bba5-1c9b73ac1628 · outbound

This paper cites Steering Language Models With Activation Engineering.

Activation Reward Models for Few-Shot Model Alignment Steering Language Models With Activation Engineering

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.491453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0166f73-c608-4948-9c7d-e922a1945039 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Activation Reward Models for Few-Shot Model Alignment Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.494467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 885d840c-9f1f-4e78-bc23-e9c322835eef · outbound

This paper cites Large language models are not fair evaluators.

Activation Reward Models for Few-Shot Model Alignment Large language models are not fair evaluators

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.154796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e8db6c18-6cf8-4e95-9d2c-fd2e7aa05d7e · outbound

This paper cites Williams.

Activation Reward Models for Few-Shot Model Alignment Williams

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.144570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5c653327-9475-4a00-8979-ce6e5ce22713 · outbound

This paper cites rewordbench: Benchmarking and improving the robustness of reward models with transformed inputs.

Activation Reward Models for Few-Shot Model Alignment rewordbench: Benchmarking and improving the robustness of reward models with transformed inputs

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.502647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2908560-f838-4916-a340-625aab08f338 · outbound

This paper cites Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models.

Activation Reward Models for Few-Shot Model Alignment Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.505501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ac0d03-a65d-4f0b-ad1a-586be8f418bb · outbound

This paper cites Zettlemoyer, and Marjan Ghazvininejad.

Activation Reward Models for Few-Shot Model Alignment Zettlemoyer, and Marjan Ghazvininejad

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.135993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a898471a-c5b5-4a9c-bb5c-6c89f20c46d1 · outbound

This paper cites Which attention heads matter for in-context learning? In Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025.

Activation Reward Models for Few-Shot Model Alignment Which attention heads matter for in-context learning? In Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.127194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fdfc61a0-60bb-41b1-8192-1c5893abc6df · outbound

This paper cites ICPL: Few-shot In-context Preference Learning via LLMs.

Activation Reward Models for Few-Shot Model Alignment ICPL: Few-shot In-context Preference Learning via LLMs

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.514668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d7b7262-f799-465f-a7e2-0578d1c3d2a1 · outbound

This paper cites Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback.

Activation Reward Models for Few-Shot Model Alignment Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.517736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8f5b9bb-35ec-4f6f-84c6-d5d8950363da · outbound

This paper cites RRHF: Rank Responses to Align Language Models with Human Feedback without tears.

Activation Reward Models for Few-Shot Model Alignment RRHF: Rank Responses to Align Language Models with Human Feedback without tears

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.520388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaef4565-ec43-4aa0-8dd9-7c359a83de49 · outbound

This paper cites Rag-reward: Optimizing rag with reward modeling and rlhf.

Activation Reward Models for Few-Shot Model Alignment Rag-reward: Optimizing rag with reward modeling and rlhf

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.523148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 206120a9-5041-4a56-a862-e9e6169bdc5a · outbound

This paper cites Generative verifiers: Reward modeling as next-token prediction.

Activation Reward Models for Few-Shot Model Alignment Generative verifiers: Reward modeling as next-token prediction

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.110641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0ac44e47-5c44-4ac3-9f80-4bbcdfea8319 · outbound

This paper cites Generative verifiers: Reward modeling as next-token prediction.

Activation Reward Models for Few-Shot Model Alignment Generative verifiers: Reward modeling as next-token prediction

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.100892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7508d138-a168-4880-8c5b-b1f4a844fd42 · outbound

This paper cites MM-RLHF: The Next Step Forward in Multimodal LLM Alignment.

Activation Reward Models for Few-Shot Model Alignment MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.531667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39407f16-bc69-4dcc-afc7-8c670e2c90e6 · outbound

This paper cites Interpreting deep visual representations via network dissection.

Activation Reward Models for Few-Shot Model Alignment Interpreting deep visual representations via network dissection

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:02:43.090900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a0b6a405-a8af-46ec-8d6b-3882c7fdc397 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Activation Reward Models for Few-Shot Model Alignment Fine-Tuning Language Models from Human Preferences

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:42.537188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97ed4056-3f3b-4b9c-8b63-918eb0850aa2 · outbound

This paper cites an unresolved cited work.

Activation Reward Models for Few-Shot Model Alignment Unresolved cited work

Reference 2025

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:02:43.352767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation df15135a-6ad7-4bf5-9d50-2dfb086d01af · inbound

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges cites this paper.

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges Activation Reward Models for Few-Shot Model Alignment

Reference 222

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:28.437494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c697a69a-b83f-45aa-8222-9158dc93e9e7 · inbound

Building a Precise Video Language with Human-AI Oversight cites this paper.

Building a Precise Video Language with Human-AI Oversight Activation Reward Models for Few-Shot Model Alignment

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:46:04.573192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e10fc225-4be8-474f-9947-e9332a7ffc41 · inbound

Multimodal Reward Hacking in Reinforcement Learning cites this paper.

Multimodal Reward Hacking in Reinforcement Learning Activation Reward Models for Few-Shot Model Alignment

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.