arXiv subjects

Yuqing Kong

Publications and source records attributed to Yuqing Kong.

At least 19 recordsLinked to original sources

arXiv2026

Finite-Sample Unbiasedly Estimable Information Monotones

Which measures of statistical dependence can be estimated unbiasedly from a fixed number of samples while satisfying the data processing inequality (DPI)? For finite alphabets, finite-sample unbiased estimability is equivalent to polynomial dependence on the distribution, and the minimum polynomial degree equals the exact sample complexity. Let $U\in\Delta_{n,m}$ be the joint-distribution matrix, with stochastic post-processing applied to the $n$-state row variable. Our main classification concerns fixed-alphabet left-sided DPI. We first prove a result beyond polynomiality: for every $n,m\ge2$, any functional that satisfies left-sided DPI, vanishes under independence, and extends to a $C^1$ function on a neighborhood of the probability simplex must vanish whenever $U$ has a zero row. If DPI is strengthened to allow changes in the processed alphabet size, every such cross-dimensional family is identically zero. For fixed-alphabet DPI, this gives a sharp trichotomy. If $n>m$, every such $C^1$-extendable functional is identically zero. If $n=m$, every nonzero admissible polynomial is divisible on the simplex by $(\det U)^2$, giving the sharp degree bound $2n$. If $n<m$, every admissible polynomial lies, modulo the simplex relation, in the square of the ideal generated by the $n\times n$ maximal minors of $U$; the sharp degree bound is again $2n$, attained by $\det(UU^\top)$. These results also show that a $C^1$-extendable functional satisfying left-sided DPI can vanish exactly at independence only when the processed variable is binary. We further prove coNP-hardness of DPI recognition for polynomial functionals and derive corresponding impossibility and exact task-complexity results for multi-task peer prediction.

cs.IT↗

arXiv2026

PMIScore: An Unsupervised Approach to Quantify Dialogue Engagement

High dialogue engagement is a crucial indicator of an effective conversation. A reliable measure of engagement could help benchmark large language models, enhance the effectiveness of human-computer interactions, or improve personal communication skills. However, quantifying engagement is challenging, since it is subjective and lacks a "gold standard". This paper proposes PMIScore, an efficient unsupervised approach to quantify dialogue engagement. It uses pointwise mutual information (PMI), which is the probability of generating a response conditioning on the conversation history. Thus, PMIScore offers a clear interpretation of engagement. As directly computing PMI is intractable due to the complexity of dialogues, PMIScore learned it through a dual form of divergence. The algorithm includes generating positive and negative dialogue pairs, extracting embeddings by large language models (LLMs), and training a small neural network using a mutual information loss function. We validated PMIScore on both synthetic and real-world datasets. Our results demonstrate the effectiveness of PMIScore in PMI estimation and the reasonableness of the PMI metric itself.

cs.CL↗

arXiv2026

Decision Aggregation under Quantal Response

The effectiveness of collective decision-making is often challenged by the bounded rationality and inherent stochasticity of individual agents. We investigate this by analyzing how to aggregate decisions from n experts, each receiving a private signal about an unknown state. Assuming signals are conditionally independent and identically distributed, we depart from the fully rational paradigm and model expert behavior using quantal response, a stochastic choice model capturing bounded rationality. Within a minimax regret framework, we show that majority voting is the optimal robust aggregator when individual rationality falls below a certain threshold. Interestingly, such groups can outperform perfectly rational agents, as their decision randomness encodes weak but informative signals lost in deterministic behavior. We validate these findings using large language models (LLMs), which naturally exhibit quantal response via their temperature parameter. Aggregating moderately stochastic LLM outputs significantly improves accuracy on complex reasoning tasks, highlighting bounded rationality not as a limitation, but as a potential strength in collective intelligence.

cs.GT↗

arXiv2026

Jailbreaking LLMs via Calibration

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on next-token prediction is modeled as a systematic distortion of a pre-alignment distribution. We cast Weak-to-Strong Jailbreaking as a forecast aggregation problem and derive an optimal aggregation strategy characterized by a Gradient Shift in the loss-induced dual space. We show that logit-arithmetic jailbreaking methods are a special case of this framework under cross-entropy loss, and derive a broader family of aggregation rules corresponding to other proper losses. We also propose a new hybrid aggregation rule. Evaluations across red-teaming benchmarks and math utility tasks using frontier models demonstrate that our approach achieves superior Attack Success Rates and lower "Jailbreak Tax" compared with existing methods, especially on the safety-hardened gpt-oss-120b.

cs.CL↗

arXiv2026

Calibration without Ground Truth

Villalobos et al. [2024] predict that publicly available human text will be exhausted within the next decade. Thus, improving models without access to ground-truth labels becomes increasingly important. We propose a label-free post-processing framework that improves a strong but miscalibrated model using a weaker yet better-calibrated reference. Our framework guarantees a strict performance improvement under any proper loss. Our approach is based on a characterization of when strict improvement is possible: when the strong and reference models are not mutually calibrated. We formalize this condition, connect it to arbitrage and no-trade results from economics, and develop an efficient Bregman projection algorithm that guarantees worst-case loss reduction without labels. Experiments on representative LLMs across varying scales demonstrate that our label-free method significantly reduces proper losses and calibration errors, achieving performance competitive with supervised baselines.

cs.LG↗

arXiv2025

Mitigating the Participation Bias by Balancing Extreme Ratings

Rating aggregation plays a crucial role in various fields, such as product recommendations, hotel rankings, and teaching evaluations. However, traditional averaging methods can be affected by participation bias, where some raters do not participate in the rating process, leading to potential distortions. In this paper, we consider a robust rating aggregation task under the participation bias. We assume that raters may not reveal their ratings with a certain probability depending on their individual ratings, resulting in partially observed samples. Our goal is to minimize the expected squared loss between the aggregated ratings and the average of all underlying ratings (possibly unobserved) in the worst-case scenario. We focus on two settings based on whether the sample size (i.e. the number of raters) is known. In the first setting, where the sample size is known, we propose an aggregator, named as the Balanced Extremes Aggregator. It estimates unrevealed ratings with a balanced combination of extreme ratings. When the sample size is unknown, we derive another aggregator, the Polarizing-Averaging Aggregator, which becomes optimal as the sample size grows to infinity. Numerical results demonstrate the superiority of our proposed aggregators in mitigating participation bias, compared to simple averaging and the spectral method. Furthermore, we validate the effectiveness of our aggregators on a real-world dataset.

cs.LG↗

arXiv2024

Benchmarking LLMs' Judgments with No Gold Standard

We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by Large Language Models (LLMs), particularly in generating informative judgments, without the need for a gold standard reference. GEM broadens the scenarios where we can benchmark LLM generation performance-from traditional ones, like machine translation and summarization, where gold standard references are readily available, to subjective tasks without clear gold standards, such as academic peer review. GEM uses a generative model to estimate mutual information between candidate and reference responses, without requiring the reference to be a gold standard. In experiments on a human-annotated dataset, GEM demonstrates competitive correlations with human scores compared to the state-of-the-art GPT-4o Examiner, and outperforms all other baselines. Additionally, GEM is more robust against strategic manipulations, such as rephrasing or elongation, which can artificially inflate scores under a GPT-4o Examiner. We also present GRE-bench (Generating Review Evaluation Benchmark) which evaluates LLMs based on how well they can generate high-quality peer reviews for academic research papers. Because GRE-bench is based upon GEM, it inherits its robustness properties. Additionally, GRE-bench circumvents data contamination problems (or data leakage) by using the continuous influx of new open-access research papers and peer reviews each year. We show GRE-bench results of various popular LLMs on their peer review capabilities using the ICLR2023 dataset.

cs.CL↗

arXiv2024

The Surprising Benefits of Base Rate Neglect in Robust Aggregation

Robust aggregation integrates predictions from multiple experts without knowledge of the experts' information structures. Prior work assumes experts are Bayesian, providing predictions as perfect posteriors based on their signals. However, real-world experts often deviate systematically from Bayesian reasoning. Our work considers experts who tend to ignore the base rate. We find that a certain degree of base rate neglect helps with robust forecast aggregation. Specifically, we consider a forecast aggregation problem with two experts who each predict a binary world state after observing private signals. Unlike previous work, we model experts exhibiting base rate neglect, where they incorporate the base rate information to degree $\lambda\in[0,1]$, with $\lambda=0$ indicating complete ignorance and $\lambda=1$ perfect Bayesian updating. To evaluate aggregators' performance, we adopt Arieli et al. (2018)'s worst-case regret model, which measures the maximum regret across the set of considered information structures compared to an omniscient benchmark. Our results reveal the surprising V-shape of regret as a function of $\lambda$. That is, predictions with an intermediate incorporating degree of base rate $\lambda<1$ can counter-intuitively lead to lower regret than perfect Bayesian posteriors with $\lambda=1$. We additionally propose a new aggregator with low regret robust to unknown $\lambda$. Finally, we conduct an empirical study to test the base rate neglect model and evaluate the performance of various aggregators.

cs.LG↗

arXiv2024

How Gold to Make the Golden Snitch: Designing the "Game Changer" in Esports

Many battling games utilize a special item (e.g. Roshan in Defense of the Ancients 2 (DOTA 2), Baron Nashor in League of Legends (LOL), Golden Snitch in Quidditch) as a potential ``Game Changer''. The reward of this item can enable the underdog to make a comeback. However, if the reward is excessively high, the whole game may devolve into a chase for the ``Game Changer''. Our research initiates with a Quidditch case study, a fictional sport in Harry Potter series, wherein we architect the Golden Snitch's reward to maximize the audience's surprise. Surprisingly, we discover that for equally competent teams, the optimal Snitch reward is zero. Moreover, we establish that under most circumstances the optimal score aligns with the game's expected duration multiplied by the teams' strength difference. Finally, we explore the correlation between the ``Game Changer's'' reward and audience surprise in Multiplayer Online Battle Arena (MOBA) games including DOTA 2 and LOL, finding that the optimal reward escalates with increasing team strength inequality.

cs.GT↗

arXiv2024

Eliciting Informative Text Evaluations with Large Language Models

Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-based reports, drawing on the recent developments in large language models. This vastly increases the applicability of peer prediction mechanisms as textual feedback is the norm in a large variety of feedback channels: peer reviews, e-commerce customer reviews, and comments on social media. We introduce two mechanisms, the Generative Peer Prediction Mechanism (GPPM) and the Generative Synopsis Peer Prediction Mechanism (GSPPM). These mechanisms utilize LLMs as predictors, mapping from one agent's report to a prediction of her peer's report. Theoretically, we show that when the LLM prediction is sufficiently accurate, our mechanisms can incentivize high effort and truth-telling as an (approximate) Bayesian Nash equilibrium. Empirically, we confirm the efficacy of our mechanisms through experiments conducted on two real datasets: the Yelp review dataset and the ICLR OpenReview dataset. We highlight the results that on the ICLR dataset, our mechanisms can differentiate three quality levels -- human-written reviews, GPT-4-generated reviews, and GPT-3.5-generated reviews in terms of expected scores. Additionally, GSPPM penalizes LLM-generated reviews more effectively than GPPM.

cs.CL↗

arXiv2024

Robust Decision Aggregation with Adversarial Experts

We consider a robust aggregation problem in the presence of both truthful and adversarial experts. The truthful experts will report their private signals truthfully, while the adversarial experts can report arbitrarily. We assume experts are marginally symmetric in the sense that they share the same common prior and marginal posteriors. The rule maker needs to design an aggregator to predict the true world state from these experts' reports, without knowledge of the underlying information structures or adversarial strategies. We aim to find the optimal aggregator that outputs a forecast minimizing regret under the worst information structure and adversarial strategies. The regret is defined by the difference in expected loss between the aggregator and a benchmark who aggregates optimally given the information structure and reports of truthful experts. We focus on binary states and reports. Under L1 loss, we show that the truncated mean aggregator is optimal. When there are at most k adversaries, this aggregator discards the k lowest and highest reported values and averages the remaining ones. For L2 loss, the optimal aggregators are piecewise linear functions. All the optimalities hold when the ratio of adversaries is bounded above by a value determined by the experts' priors and posteriors. The regret only depends on the ratio of adversaries, not on their total number. For hard aggregators that output a decision, we prove that a random version of the truncated mean is optimal for both L1 and L2. This aggregator randomly follows a remaining value after discarding the $k$ lowest and highest reported values. We extend the hard aggregator to multi-state setting. We evaluate our aggregators numerically in an ensemble learning task. We also obtain negative results for general adversarial aggregation problems under broader information structures and report spaces.

cs.LG↗

arXiv2024

Peer Expectation in Robust Forecast Aggregation: The Possibility/Impossibility

Recently a growing literature study a new forecast aggregation setting where each forecaster is additionally asked ``what's your expectation for the average of other forecasters' forecasts?''. However, most theoretic results in this setting focus on the scenarios where the additional second-order information helps optimally aggregate the forecasts. Here we adopt an adversarial approach and follow the robust forecast aggregation framework proposed by Arielia, Babichenkoa, and Smorodinsky 2018. We delicately analyze the possibility/impossibility of the new setting when there are two forecasters that either are refinement-ordered or receive conditionally independent and identically distributed (c.i.i.d.) signals. We also extend the setting to a higher level of expectation setting where we can additionally ask ``what's your expectation for the other forecaster's expectation for ...''. The results show that in the above settings, the additional second-order information can significantly improve the aggregation accuracy, and the higher the order, the higher the improvement.

cs.GT↗

arXiv2024

Algorithmic Robust Forecast Aggregation

Forecast aggregation combines the predictions of multiple forecasters to improve accuracy. However, the lack of knowledge about forecasters' information structure hinders optimal aggregation. Given a family of information structures, robust forecast aggregation aims to find the aggregator with minimal worst-case regret compared to the omniscient aggregator. Previous approaches for robust forecast aggregation rely on heuristic observations and parameter tuning. We propose an algorithmic framework for robust forecast aggregation. Our framework provides efficient approximation schemes for general information aggregation with a finite family of possible information structures. In the setting considered by Arieli et al. (2018) where two agents receive independent signals conditioned on a binary state, our framework also provides efficient approximation schemes by imposing Lipschitz conditions on the aggregator or discrete conditions on agents' reports. Numerical experiments demonstrate the effectiveness of our method by providing a nearly optimal aggregator in the setting considered by Arieli et al. (2018).

cs.LG↗

arXiv2023

Calibrating "Cheap Signals" in Peer Review without a Prior

Peer review lies at the core of the academic process, but even well-intentioned reviewers can still provide noisy ratings. While ranking papers by average ratings may reduce noise, varying noise levels and systematic biases stemming from ``cheap'' signals (e.g. author identity, proof length) can lead to unfairness. Detecting and correcting bias is challenging, as ratings are subjective and unverifiable. Unlike previous works relying on prior knowledge or historical data, we propose a one-shot noise calibration process without any prior information. We ask reviewers to predict others' scores and use these predictions for calibration. Assuming reviewers adjust their predictions according to the noise, we demonstrate that the calibrated score results in a more robust ranking compared to average ratings, even with varying noise levels and biases. In detail, we show that the error probability of the calibrated score approaches zero as the number of reviewers increases and is significantly lower compared to average ratings when the number of reviewers is small.

cs.GT↗

arXiv2023

Learning against Non-credible Auctions

The standard framework of online bidding algorithm design assumes that the seller commits himself to faithfully implementing the rules of the adopted auction. However, the seller may attempt to cheat in execution to increase his revenue if the auction belongs to the class of non-credible auctions. For example, in a second-price auction, the seller could create a fake bid between the highest bid and the second highest bid. This paper focuses on one such case of online bidding in repeated second-price auctions. At each time $t$, the winner with bid $b_t$ is charged not the highest competing bid $d_t$ but a manipulated price $p_t = α_0 d_t + (1-α_0) b_t$, where the parameter $α_0 \in [0, 1]$ in essence measures the seller's credibility. Unlike classic repeated-auction settings where the bidder has access to samples $(d_s)_{s=1}^{t-1}$, she can only receive mixed signals of $(b_s)_{s=1}^{t-1}$, $(d_s)_{s=1}^{t-1}$ and $α_0$ in this problem. The task for the bidder is to learn not only the bid distributions of her competitors but also the seller's credibility. We establish regret lower bounds in various information models and provide corresponding online bidding algorithms that can achieve near-optimal performance. Specifically, we consider three cases of prior information based on whether the credibility $α_0$ and the distribution of the highest competing bids are known. Our goal is to characterize the landscape of online bidding in non-credible auctions and understand the impact of the seller's credibility on online bidding algorithm design under different information structures.

cs.GT↗

arXiv2023

Robust Decision Aggregation with Second-order Information

We consider a decision aggregation problem with two experts who each make a binary recommendation after observing a private signal about an unknown binary world state. An agent, who does not know the joint information structure between signals and states, sees the experts' recommendations and aims to match the action with the true state. Under the scenario, we study whether supplemented additionally with second-order information (each expert's forecast on the other's recommendation) could enable a better aggregation. We adopt a minimax regret framework to evaluate the aggregator's performance, by comparing it to an omniscient benchmark that knows the joint information structure. With general information structures, we show that second-order information provides no benefit. No aggregator can improve over a trivial aggregator, which always follows the first expert's recommendation. However, positive results emerge when we assume experts' signals are conditionally independent given the world state. When the aggregator is deterministic, we present a robust aggregator that leverages second-order information, which can significantly outperform counterparts without it. Second, when two experts are homogeneous, by adding a non-degenerate assumption on the signals, we demonstrate that random aggregators using second-order information can surpass optimal ones without it. In the remaining settings, the second-order information is not beneficial. We also extend the above results to the setting when the aggregator's utility function is more general.

cs.GT↗

arXiv2023

Multistable Perception, False Consensus, and Information Complements

This paper presents a distributed communication model to investigate multistable perception, where a stimulus gives rise to multiple competing perceptual interpretations. We formalize stable perception as consensus achieved through components exchanging information. Our key finding is that relationships between components influence monostable versus multistable perceptions. When components contain substitute information about the prediction target, stimuli display monostability. With complementary information, multistability arises. We then analyze phenomena like order effects and switching costs. Finally, we provide two additional perspectives. An optimization perspective balances accuracy and communication costs, relating stability to local optima. A Prediction market perspective highlights the strategic behaviors of neural coordination and provides insights into phenomena like rivalry, inhibition, and mental disorders. The two perspectives demonstrate how relationships among components influence perception costs, and impact competition and coordination behaviors in neural dynamics.

cs.GT↗

arXiv2023

Learning to Bid in Repeated First-Price Auctions with Budgets

Budget management strategies in repeated auctions have received growing attention in online advertising markets. However, previous work on budget management in online bidding mainly focused on second-price auctions. The rapid shift from second-price auctions to first-price auctions for online ads in recent years has motivated the challenging question of how to bid in repeated first-price auctions while controlling budgets. In this work, we study the problem of learning in repeated first-price auctions with budgets. We design a dual-based algorithm that can achieve a near-optimal $\widetilde{O}(\sqrt{T})$ regret with full information feedback where the maximum competing bid is always revealed after each auction. We further consider the setting with one-sided information feedback where only the winning bid is revealed after each auction. We show that our modified algorithm can still achieve an $\widetilde{O}(\sqrt{T})$ regret with mild assumptions on the bidder's value distribution. Finally, we complement the theoretical results with numerical experiments to confirm the effectiveness of our budget management policy.

cs.GT↗