REVIEW 15 cited by
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
While existing alignment paradigms have been integral in developing large language models (LLMs), LLMs often learn an averaged human preference and struggle to model diverse preferences across cultures, demographics, and communities. We propose Modular Pluralism, a modular framework based on multi-LLM collaboration for pluralistic alignment: it "plugs into" a base LLM a pool of smaller but specialized community LMs, where models collaborate in distinct modes to flexibility support three modes of pluralism: Overton, steerable, and distributional. Modular Pluralism is uniquely compatible with black-box LLMs and offers the modular control of adding new community LMs for previously underrepresented communities. We evaluate Modular Pluralism with six tasks and four datasets featuring questions/instructions with value-laden and perspective-informed responses. Extensive experiments demonstrate that Modular Pluralism advances the three pluralism objectives across six black-box and open-source LLMs. Further analysis reveals that LLMs are generally faithful to the inputs from smaller community LLMs, allowing seamless patching by adding a new community LM to better cover previously underrepresented communities.
Forward citations
Cited by 15 Pith papers
-
The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse
Across 1,980 five-agent LLM runs on citizen-assembly topics, LLM groups match human procedural talk but show one-third the perspective diversity, weak topic-dependent consistency gains, and reversed convergence dynamics.
-
PLURAL: A Global Dataset for Value Alignment
Synthetic preference data generated from the Integrated Values Survey preserves cross-country value differences and enables DPO fine-tuning that improves LLM cultural alignment across five countries.
-
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
Personalized RewardBench reveals that state-of-the-art reward models reach only 75.94% accuracy on personalized preferences and shows stronger correlation with downstream BoN and PPO performance than prior benchmarks.
-
The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models
LLMs align with human moral judgments only under high consensus, concentrate on a narrow set of moral values, and the profile-based prompting method's reported improvement is evaluated in-sample.
-
Pairwise Calibrated Rewards for Pluralistic Alignment
A small ensemble of reward functions can be trained to match pairwise human preference frequencies, offering a practical route to pluralistic AI alignment.
-
Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity
Fair-PP contributes a synthetic persona-anchored preference dataset for social equity and a reweighted DPO/SFT alignment method that outperforms baselines on LLM-similarity tests.
-
Evaluating the Prompt Steerability of Large Language Models
A formal benchmark with steerability indices shows that six open-weight LLMs are only partially steerable by prompting, with strong baseline skew and directional asymmetry.
-
Epistemic diversity across language models mitigates knowledge collapse
In repeated self-training loops on Wikitext2, ecosystems of four small language models show lower average perplexity than one, two, or sixteen models, but the paper's broader claims about monotonic optima, robustness,...
-
How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs
A leader LLM trained with a GRPO variant that conditions on frozen agent responses improves both collaborative and zero-shot accuracy on BBH, MATH, and MMLU.
-
Personalized Preference Fine-tuning of Diffusion Models
PPD fine-tunes a single diffusion model to follow per-user preferences by conditioning on VLM-extracted embeddings, reporting 76-81% win rates over Stable Cascade with four examples per user.
-
Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach
LLM bias scores change depending on whether 'unbiased' means equal treatment across groups or close alignment with US workforce statistics.
-
Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration
A survey of multi-LLM systems in edge computing, covering architectures, enabling technologies, trust mechanisms, applications, and open datasets for edge general intelligence.
-
Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead
A literature review organizes LLM development into a six-phase software engineering lifecycle and identifies challenges and research directions for each phase.
-
Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise
A multi-agent router that selects culturally specialized LLM personas reports a jump in self-scored cultural alignment from 0.208 to 0.820, but the metric and the claimed method are not independently validated.
-
OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models
The paper advocates protecting and leveraging OpenReview's peer review corpus as a community asset for LLM-based review assistance, benchmarks, and alignment.
Discussion (0). Continue with ORCID to comment.