extract: 2026-02-00-an-differentiable-social-choice
Pentagon-Agent: Ganymede <F99EBFA6-547B-4096-BEEA-1D59C3E4028A>
This commit is contained in:
Teleo Agents
parent
29a7e87561
commit
f7aceee9bb
3 changed files with 27 additions and 19 deletions
|
|
@ -39,6 +39,12 @@ RLCF makes the social choice mechanism explicit through the bridging algorithm (
|
|||
|
||||
Comprehensive February 2026 survey by An & Du documents that contemporary ML systems implement social choice mechanisms implicitly across RLHF, participatory budgeting, and liquid democracy applications, with 18 identified open problems spanning incentive guarantees and pluralistic preference aggregation.
|
||||
|
||||
|
||||
### Additional Evidence (confirm)
|
||||
*Source: [[2026-02-00-an-differentiable-social-choice]] | Added: 2026-03-16*
|
||||
|
||||
An & Du's February 2026 comprehensive survey explicitly positions 'AI Alignment as Social Choice' as one of six core domains in differentiable social choice, with RLHF as the central example. The survey identifies 18 open problems spanning incentive guarantees, robustness, certification, and pluralistic preference aggregation—confirming that treating RLHF as social choice is now an established research paradigm, not a fringe claim.
|
||||
|
||||
---
|
||||
|
||||
Relevant Notes:
|
||||
|
|
|
|||
|
|
@ -1,40 +1,31 @@
|
|||
{
|
||||
"rejected_claims": [
|
||||
{
|
||||
"filename": "rlhf-implements-implicit-social-choice-without-normative-scrutiny.md",
|
||||
"filename": "impossibility-theorems-become-optimization-tradeoffs-in-differentiable-social-choice.md",
|
||||
"issues": [
|
||||
"missing_attribution_extractor"
|
||||
]
|
||||
},
|
||||
{
|
||||
"filename": "impossibility-results-become-optimization-tradeoffs-in-learned-mechanisms.md",
|
||||
"issues": [
|
||||
"missing_attribution_extractor"
|
||||
]
|
||||
},
|
||||
{
|
||||
"filename": "inverse-mechanism-learning-can-detect-implicit-social-choice-functions.md",
|
||||
"filename": "inverse-mechanism-learning-can-detect-implicit-social-choice-functions-in-deployed-systems.md",
|
||||
"issues": [
|
||||
"missing_attribution_extractor"
|
||||
]
|
||||
}
|
||||
],
|
||||
"validation_stats": {
|
||||
"total": 3,
|
||||
"total": 2,
|
||||
"kept": 0,
|
||||
"fixed": 5,
|
||||
"rejected": 3,
|
||||
"fixed": 3,
|
||||
"rejected": 2,
|
||||
"fixes_applied": [
|
||||
"rlhf-implements-implicit-social-choice-without-normative-scrutiny.md:set_created:2026-03-16",
|
||||
"rlhf-implements-implicit-social-choice-without-normative-scrutiny.md:stripped_wiki_link:universal-alignment-is-mathematically-impossible-because-Arr",
|
||||
"impossibility-results-become-optimization-tradeoffs-in-learned-mechanisms.md:set_created:2026-03-16",
|
||||
"impossibility-results-become-optimization-tradeoffs-in-learned-mechanisms.md:stripped_wiki_link:universal-alignment-is-mathematically-impossible-because-Arr",
|
||||
"inverse-mechanism-learning-can-detect-implicit-social-choice-functions.md:set_created:2026-03-16"
|
||||
"impossibility-theorems-become-optimization-tradeoffs-in-differentiable-social-choice.md:set_created:2026-03-16",
|
||||
"impossibility-theorems-become-optimization-tradeoffs-in-differentiable-social-choice.md:stripped_wiki_link:universal-alignment-is-mathematically-impossible-because-Arr",
|
||||
"inverse-mechanism-learning-can-detect-implicit-social-choice-functions-in-deployed-systems.md:set_created:2026-03-16"
|
||||
],
|
||||
"rejections": [
|
||||
"rlhf-implements-implicit-social-choice-without-normative-scrutiny.md:missing_attribution_extractor",
|
||||
"impossibility-results-become-optimization-tradeoffs-in-learned-mechanisms.md:missing_attribution_extractor",
|
||||
"inverse-mechanism-learning-can-detect-implicit-social-choice-functions.md:missing_attribution_extractor"
|
||||
"impossibility-theorems-become-optimization-tradeoffs-in-differentiable-social-choice.md:missing_attribution_extractor",
|
||||
"inverse-mechanism-learning-can-detect-implicit-social-choice-functions-in-deployed-systems.md:missing_attribution_extractor"
|
||||
]
|
||||
},
|
||||
"model": "anthropic/claude-sonnet-4.5",
|
||||
|
|
|
|||
|
|
@ -15,6 +15,10 @@ processed_by: theseus
|
|||
processed_date: 2026-03-16
|
||||
enrichments_applied: ["rlhf-is-implicit-social-choice-without-normative-scrutiny.md", "single-reward-rlhf-cannot-align-diverse-preferences-because-alignment-gap-grows-proportional-to-minority-distinctiveness.md"]
|
||||
extraction_model: "anthropic/claude-sonnet-4.5"
|
||||
processed_by: theseus
|
||||
processed_date: 2026-03-16
|
||||
enrichments_applied: ["rlhf-is-implicit-social-choice-without-normative-scrutiny.md"]
|
||||
extraction_model: "anthropic/claude-sonnet-4.5"
|
||||
---
|
||||
|
||||
## Content
|
||||
|
|
@ -62,3 +66,10 @@ EXTRACTION HINT: Focus on "RLHF is implicit social choice" and "impossibility as
|
|||
- Survey identifies 18 open problems in the field
|
||||
- Six interconnected domains surveyed: differentiable economics, neural social choice, AI alignment as social choice, participatory budgeting, liquid democracy, inverse mechanism learning
|
||||
- Field of differentiable social choice emerged within last 5 years
|
||||
|
||||
|
||||
## Key Facts
|
||||
- An & Du published 'Methods and Open Problems in Differentiable Social Choice' in February 2026
|
||||
- Survey identifies 18 open problems in differentiable social choice
|
||||
- Six domains surveyed: differentiable economics, neural social choice, AI alignment as social choice, participatory budgeting, liquid democracy, inverse mechanism learning
|
||||
- Field of differentiable social choice emerged within last 5 years according to survey authors
|
||||
|
|
|
|||
Loading…
Reference in a new issue