WARP: Wasserstein-Aligned RAG for Population Opinions

• URL: http://arxiv.org/abs/2608.22859v1
• Date: Mon, 24 Aug 2026 06:41:23 GMT
• Title: WARP: Wasserstein-Aligned RAG for Population Opinions
• Abstract summary: WARP calibrates retrieved evidence to the population's opinion distribution.<n>We develop three variants for dense, sparse, and variable candidate pools.<n> WARP's domain-matched variants reduce distributional error by at least 43% with sub-second latency.
• Score: 0.9882967349104086
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: RAG systems are increasingly used to summarize what large collections of documents say. A user asks "What do people think about X?" and receives an answer that reads as consensus. But standard top-k retrieval ranks documents by query similarity, not by how faithfully they represent the population, so minority views quietly disappear. Existing fixes fall short. Diversity re-rankers like MMR and DPP spread retrieved documents apart, but with no target distribution to aim for. Calibration methods based on KL or JS divergence do target one, yet treat opinion bins as unordered: confusing strong positive with strong negative costs no more than an adjacent-bin miss. We introduce WARP, a family of post-retrieval algorithms that calibrate retrieved evidence to the population's opinion distribution. WARP first recovers underrepresented opinions that cosine ranking may bury, then uses Wasserstein-1 distance to select documents whose sentiment-intensity distribution matches the population target, capturing the ordinal structure ignored by KL and JS divergence. We develop three variants for dense, sparse, and variable candidate pools, trading off calibration quality and speed. Across three review domains spanning 35K documents, 156 queries, and 26 entities, WARP's domain-matched variants reduce distributional error by at least 43% with sub-second latency. These gains carry through to generation: a five-judge LLM panel prefers WARP-generated answers in 86% of decided comparisons at k <= 5.

Related papers

• When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making [5.335515762403034]
  LLM judges, voting rules, and electoral rules rely on forward reasoning to map evidence to labels in one direction.<n>We construct a reverse posterior for each instance through Bayesian backward reasoning from an explicit likelihood.<n>Because estimates from different factorizations may tend to share the same error less often, we use Jensen-Shannon divergence to rank agents by cross-path consistency.
  arXiv  Detail & Related papers  (2026-09-10T15:27:58Z)
• Spurious Advantage Hidden in GRPO [36.79136670827014]
  Group Relative Policy Optimization is studied for reinforcement learning with verifiable rewards.<n>An overlooked case shares the same surface: a rollout may land on it by guessing, and the formula still assigns a high magnitude.<n>This arises in three cases: bounded-answer tasks with a small candidate set; open-answer sets hosting bounded sub-cases; and search agents whose budget opens many paths to the same answer.<n>We propose SIGNBALANCE, whose magnitude is composition-free: it keeps the verifier sign, uses a global scale, and restores zero-mean balance via a stop-gradient per-class rescaling
  arXiv  Detail & Related papers  (2026-09-03T16:37:31Z)
• BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms [22.217909582731505]
  Retrieval-augmented generation (RAG) spans lexical and dense retrieval, graph-based indexing, and agentic search.<n>We present a controlled study that varies corpus size along 28 strictly nested tiers spanning roughly 450-fold.<n>We measure official accuracy, construction and query tokens, and latency.
  arXiv  Detail & Related papers  (2026-07-29T05:46:11Z)
• AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution [11.790070440436294]
  Alpha mining holds the scoring function fixed and varies the search algorithm over it.<n>A search that converges against a fixed scorer overfits whatever the scorer cannot penalize, a primary cause of the out-of-sample generalization gap.<n>We treat the scoring function as a search artifact alongside the alpha factors and study what conditions make this joint search admissible.
  arXiv  Detail & Related papers  (2026-06-28T04:41:00Z)
• AgentFairBench: Do LLM Agents Discriminate When They Act? [2.3004655342211078]
  AgentFairBench is a cheap, reproducible, multi-domain benchmark for demographic disparity in the actions of LLM agents.<n>It spans three regulator-anchored domains: hiring, lending, and medical triage.<n>A NumPy-only harness computes counterfactual flip rate, mean absolute score difference (MASD), action-rate disparity, and tool-invocation disparity.
  arXiv  Detail & Related papers  (2026-06-15T13:50:26Z)
• Instance-Optimal Estimation with Multiple LLM Judges on a Budget [84.31744861038106]
  We formalize this question as *budgeted heteroskedastic multi-judge estimation*.<n>Given $K$ prompt-response pairs, $J$ judges with known costs, and unknown query-judge variances, the goal is to estimate a bounded score vector while minimizing an $ell_p$-error.<n>We prove that EST-IVWE matches the oracle IVWE rate up to lower-order terms in the budget.
  arXiv  Detail & Related papers  (2026-05-22T08:26:08Z)
• OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation [53.88666485159289]
  We introduce OpenDeepThink, a population-based test-time compute framework that selects via pairwise Bradley-Terry comparison.<n>OpenDeepThink raises Gemini 3.1 Pro's effective Codeforces Elo by +405 points in eight sequential LLM-call rounds.<n>We release CF-73, a curated set of 73 expert-rated Codeforces problems with International Grandmaster annotation and 99% local-evaluation agreement against the official verdict.
  arXiv  Detail & Related papers  (2026-05-14T17:57:40Z)
• Evidence-based Distributional Alignment for Large Language Models [58.65469623911573]
  We propose Evi-DA, an evidence-based alignment technique that improves the fidelity and robustness of LLM-based distribution estimation.<n>Given a target country, Evi-DA retrieves related World Values Survey items and their answer distributions, predicts a coarse Welzel value signature for each option, and infers the country-conditioned answer distribution in a structured format.
  arXiv  Detail & Related papers  (2026-03-03T03:34:06Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality [53.03186946689658]
  Test-time scaling with verification has shown promise in improving the performance of large language models.<n>The effect of verification manifests through interactions of three quantities: (i) the generator's coverage, (ii) the verifier's region of convergence (ROC), and (iii) the sampling algorithm's sub-optimality.<n>We frame verifiable test-time scaling as a transport problem. This characterizes the interaction of coverage, ROC, and sub-optimality.
  arXiv  Detail & Related papers  (2025-10-21T18:05:42Z)
• Large Language Models are not Fair Evaluators [60.27164804083752]
  We find that the quality ranking of candidate responses can be easily hacked by altering their order of appearance in the context. This manipulation allows us to skew the evaluation result, making one model appear considerably superior to the other. We propose a framework with three simple yet effective strategies to mitigate this issue.
  arXiv  Detail & Related papers  (2023-05-29T07:41:03Z)

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.