Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers

• URL: http://arxiv.org/abs/2609.05189v2
• Date: Mon, 07 Sep 2026 08:25:42 GMT
• Title: Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers
• Abstract summary: We present FlexPension-LLM, the first domain-specialized large language model for a hierarchical pension-enrollment prediction task among flexible workers in China.<n>We introduce DKI-RDistill, which injects policy-grounded cues into the prompt, including Probit-derived marginal effects and hukou-province pension rules.<n>The method then uses LoRA/SFT to distill rationale-augmented supervision into an open-weight MoE student, with teacher errors corrected by regenerating those cases.
• Score: 7.812925339338843
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Assessing the impacts of social policy changes is a widely acknowledged challenge for policymakers. Econometric methods can be unreliable when extrapolating to hypothetical scenarios, while field pilot programs are highly costly. In this paper, we propose using large language models (LLMs) as policy-assessment tools adapted from general-purpose models. We present FlexPension-LLM, the first domain-specialized large language model for a hierarchical pension-enrollment prediction task among flexible workers in China, and introduce DKI-RDistill, which injects policy-grounded cues into the prompt, including Probit-derived marginal effects and hukou-province pension rules. The method then uses LoRA/SFT to distill rationale-augmented supervision into an open-weight MoE student, with teacher errors corrected by regenerating those cases under ground-truth labels. On a CHFS 2019 blind split, FlexPension-LLM achieves 0.9316 Composite F1, surpassing its Claude Sonnet 4.5 teacher and 15 of 17 baselines, and is statistically indistinguishable from Claude Opus 4.6. Across four external surveys, it averages 0.7549 Composite F1 and shows the narrowest performance range among the strongest systems. Component analysis shows that gains come mainly from policy-grounded cue injection and error-filtered supervision, while rationales provide decision traces that can be checked against policy rules.

Related papers

• FIRE-VLA: Failure-Informed Self-Evolution for Vision-Language-Action Models in Autonomous Driving [1.4298580363875282]
  Group relative policy optimization learns from reward differences within each rollout group.<n>Fire-VLA converts unresolved failures into privileged supervision for the next policy.<n>On 6,019 examples from 150 held-out nuScenes scenes, FIRE-VLA retains comparable single-sample planning.
  arXiv  Detail & Related papers  (2026-08-13T15:53:24Z)
• Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning [58.088509347353465]
  Reinforcement learning (RL) fine-tuning is widely used in language model training.<n>We propose a game-theoretic framework that gives this trade-off an explicit statistical interpretation.
  arXiv  Detail & Related papers  (2026-07-29T00:19:09Z)
• Ontology-Amplified Distillation and Contextuality Auditing for Sovereign Enterprise Language Models: A Combined Proof-of-Mechanism and Negative-Results Method Study [0.0]
  This paper combines two related FAOS studies into one mechanism-and-control article.<n>First, it reports a reduced-power proof-of-mechanism study of ontology-amplified distillation.<n>Second, the paper consolidates a contextuality-audit method for enterprise-agent routing.
  arXiv  Detail & Related papers  (2026-07-11T15:42:40Z)
• Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients [89.89504265663057]
  Zone of Proximal Policy Optimization (ZPPO) is inspired by Vygotsky's zone of proximal development.<n>ZPPO pairs one correct teacher response with one incorrect student response as anonymized candidates the student must discriminate.<n>A prompt replay buffer recirculates each hard question until it either graduates-the student's mean rollout accuracy on it reaches half- or is FIFO-evicted.
  arXiv  Detail & Related papers  (2026-06-16T17:46:02Z)
• MANTA: Multi-turn Assessment for Nonhuman Thinking & Alignment [0.1452394725421793]
  MANTA is a dynamic multi-turn evaluation framework built on the Inspect AI platform.<n>We present preliminary results from evaluations of claude-sonnet-4-20250514 and openai/gpt-4o.<n>We additionally present STYLEJUDGE, a controlled four-judge study demonstrating systematic format bias in LLM-as-judge evaluation.
  arXiv  Detail & Related papers  (2026-04-18T19:51:32Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only [70.43369087819332]
  Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models with human-annotated demonstrations.<n>We propose Self-Rewarding PPO, a novel fine-tuning method that leverages on-policy techniques to enhance generalization performance.
  arXiv  Detail & Related papers  (2025-10-24T02:02:13Z)
• Mind the Gap: Data Rewriting for Stable Off-Policy Supervised Fine-Tuning [33.899779762210976]
  Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem.<n>Existing methods mitigate this issue with KL penalties or clipping, which passively updates rather than actively reducing the gap.<n>We propose a simple yet effective data rewriting framework that proactively shrinks the policy gap before training.
  arXiv  Detail & Related papers  (2025-09-18T17:02:30Z)
• Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning [3.0294344089697596]
  We release Op-Fed, a dataset of 1044 human-annotated sentences and their contexts.<n>We developed a five-stage hierarchical schema to isolate aspects of opinion, monetary policy, and stance towards monetary policy.<n>We found a top-performing, closed-weight LLM achieves 0.80 zero-shot accuracy in opinion classification but only 0.61 zero-shot accuracy classifying stance towards monetary policy.
  arXiv  Detail & Related papers  (2025-09-16T21:07:17Z)
• Pre-Trained Policy Discriminators are General Reward Models [81.3974586561645]
  We propose a scalable pre-training method named Policy Discriminative Learning (POLAR)<n>POLAR trains a reward model (RM) to discern identical policies and discriminate different ones.<n> Empirical results show that POLAR substantially outperforms traditional non-pre-trained methods.
  arXiv  Detail & Related papers  (2025-07-07T16:56:31Z)
• Fine-Tuning Language Models with Advantage-Induced Policy Alignment [80.96507425217472]
  We propose a novel algorithm for aligning large language models to human preferences. We show that it consistently outperforms PPO in language tasks by a large margin. We also provide a theoretical justification supporting the design of our loss function.
  arXiv  Detail & Related papers  (2023-06-04T01:59:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.