arXiv subjects

Bryan Li

Publications and source records attributed to Bryan Li.

At least 19 recordsLinked to original sources

arXiv2026

DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation

Evaluation of long-form, citation-backed reports has lately received significant attention due to the wide-scale adoption of retrieval-augmented generation (RAG) systems. Core to many evaluation frameworks is the use of atomic facts, or nuggets, to assess a report's coverage of query-relevant information attested in the underlying collection. While nuggets have traditionally been represented as short statements, recent work has used question-answer (QA) representations, enabling fine-grained evaluations that decouple the information need (i.e. the question) from the potentially diverse content that satisfies it (i.e. its answers). A persistent challenge for nugget-based evaluation is the need to manually curate sets of nuggets for each topic in a test collection -- a laborious process that scales poorly to novel information needs. This challenge is acute in cross-lingual settings, where information is found in multilingual source documents. Accordingly, we introduce DoGMaTiQ, a pipeline for generating high-quality QA-based nugget sets in three stages: (1) document-grounded nugget generation, (2) paraphrase clustering, and (3) nugget subselection based on principled quality criteria. We integrate DoGMaTiQ nuggets with AutoArgue -- a recent nugget-based evaluation framework -- to enable fully automatic evaluation of generated reports. We conduct extensive experiments on two cross-lingual TREC shared tasks, NeuCLIR and RAGTIME, showing strong rank correlations with both human-in-the-loop and fully manual judgments. Finally, detailed analysis of our pipeline reveals that a strong LLM nugget generator is key, and that the system rankings induced by DoGMaTiQ are robust to outlier systems. We facilitate future research in report evaluation by publicly releasing our code and artifacts at https://github.com/manestay/dogmatiq.

cs.CL↗

arXiv2026

Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models

Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these models primarily expose marginal conditional distributions and do not explicitly represent inter-variable dependence. We propose a neural framework for estimating pairwise conditional mutual information (MI) directly from the hidden states of a pretrained MDM, using ground-truth MI computed from the model's own conditional distributions for supervision. The resulting estimator captures the model's internal belief about dependency structure and predicts the full MI matrix in a single forward pass, enabling MI-guided parallel decoding by identifying conditionally independent subsets of variables. We evaluate our approach on Sudoku and protein sequence generation with ESM-C, where the MI maps recover known structural constraints and enable a 3-5x magnitude reduction in inference-time forward passes compared to sequential decoding, while preserving generative quality and outperforming entropy-based parallelization methods.

cs.LG↗

arXiv2026

Incorporating Q&A Nuggets into Retrieval-Augmented Generation

RAGE systems integrate ideas from automatic evaluation (E) into Retrieval-augmented Generation (RAG). As one such example, we present Crucible, a Nugget-Augmented Generation System that preserves explicit citation provenance by constructing a bank of Q&A nuggets from retrieved documents and uses them to guide extraction, selection, and report generation. Reasoning on nuggets avoids repeated information through clear and interpretable Q&A semantics - instead of opaque cluster abstractions - while maintaining citation provenance throughout the entire generation process. Evaluated on the TREC NeuCLIR 2024 collection, our Crucible system substantially outperforms Ginger, a recent nugget-based RAG system, in nugget recall, density, and citation grounding.

cs.IR↗

arXiv2026

Insider Knowledge: How Much Can RAG Systems Gain from Evaluation Secrets?

RAG systems are increasingly evaluated and optimized using LLM judges, an approach that is rapidly becoming the dominant paradigm for system assessment. Nugget-based approaches in particular are now embedded not only in evaluation frameworks but also in the architectures of RAG systems themselves. While this integration can lead to genuine improvements, it also creates a risk of faulty measurements due to circularity. In this paper, we investigate this risk through comparative experiments with nugget-based RAG systems, including Ginger and Crucible, against strong baselines such as GPT-Researcher. By deliberately modifying Crucible to generate outputs optimized for an LLM judge, we show that near-perfect evaluation scores can be achieved when elements of the evaluation - such as prompt templates or gold nuggets - are leaked or can be predicted. Our results highlight the importance of blind evaluation settings and methodological diversity to guard against mistaking metric overfitting for genuine system progress.

cs.IR↗

arXiv2025

Investigating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries

Real-world use cases often present RAG systems with complex queries for which relevant information is missing from the corpus or is incomplete. In these settings, RAG systems must be able to reject unanswerable, out-of-scope queries and identify failures of retrieval and multi-hop reasoning. Despite this, existing RAG benchmarks rarely reflect realistic task complexity for multi-hop or out-of-scope questions, which often can be cheated via disconnected reasoning (i.e., solved without genuine multi-hop inference) or require only simple factual recall. This limits the ability for such benchmarks to uncover limitations of existing RAG systems. To address this gap, we present the first pipeline for automatic, difficulty-controlled creation of un$\underline{c}$heatable, $\underline{r}$ealistic, $\underline{u}$nanswerable, and $\underline{m}$ulti-hop $\underline{q}$uerie$\underline{s}$ (CRUMQs), adaptable to any corpus and domain. We use our pipeline to create CRUMQs over two popular RAG datasets and demonstrate its effectiveness via benchmark experiments on leading retrieval-augmented LLMs. Results show that compared to prior RAG benchmarks, CRUMQs are highly challenging for RAG systems and achieve up to 81.0\% reduction in cheatability scores. More broadly, our pipeline offers a simple way to enhance benchmark difficulty and drive development of more capable RAG systems.

cs.CL↗

arXiv2025

Auto-ARGUE: LLM-Based Report Generation Evaluation

Generation of citation-backed reports is a primary use case for retrieval-augmented generation (RAG) systems. While open-source evaluation tools exist for various RAG tasks, tools designed for report generation are lacking. Accordingly, we introduce Auto-ARGUE, a robust LLM-based implementation of the recently proposed ARGUE framework for report generation evaluation. We present analysis of Auto-ARGUE on the report generation pilot task from the TREC 2024 NeuCLIR track and on two tasks from the TREC 2024 RAG track, showing good system-level correlations with human judgments. Additionally, we release ARGUE-Viz, a web app for visualization and fine-grained analysis of Auto-ARGUE judgments and scores.

cs.IR↗

arXiv2025

On the set of atoms and strong atoms in additive monoids of cyclic semidomains

Let $M$ be a cancellative and commutative monoid. A non-invertible element of $M$ is called an atom (or irreducible element) if it cannot be factored into two non-invertible elements, while an atom $a$ of $M$ is called strong if $a^n$ has a unique factorization in $M$ for every $n \in \mathbb{N}$. The monoid $M$ is atomic if every non-invertible element factors into finitely many atoms (repetitions allowed). For an algebraic number $\alpha$, we let $M_\alpha$ denote the additive monoid of the subsemiring $\mathbb{N}_0[\alpha]$ of $\mathbb{C}$. The atomic structure of $M_\alpha$ reflects intricate interactions between algebraic number theory and additive semigroup theory. For $m, n \in \mathbb{N}_0 \cup \{ \infty \}$ (with $m \le n$), the pair $(m,n)$ is called realizable if there exists an algebraic number $\alpha \in \mathbb{C}$ such that $M_\alpha$ has $m$ strong atoms and $n$ atoms. Our primary goal is to identify classes of realizable pairs with the long-term goal of providing a complete description of the full set of realizable pairs.

math.AC↗

arXiv2025

Flat bands, Dirac cones, and higher-order band crossings in twisted multilayer graphene

For the chiral limit of two sheets of $n$-layer Bernal-stacked graphene established in the Physical Review Letters arXiv:2109.10325 and arXiv:2109.11514, we prove a trichotomy: depending on the twisting angle, we have either (1) generically, the band crossing of the first two bands is of order $n$; or (2) at a discrete set of magic angles, the first two bands are completely flat; or (3) for another discrete set of twisting parameters, the bands exhibit Dirac cones. This new mathematical discovery disproves the common belief in physics that such a twisted multilayer graphene model can only have higher order band crossings or flat bands, and it leads to a new type of topological phase transition.

math-ph↗

arXiv2025

Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale

Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks -- from offering writing support to delivering tailored recommendations or consultations. Over time, the interaction history between a user and an LLM can provide extensive information about an individual's traits and preferences. However, open questions remain on how well LLMs today can effectively leverage such history to (1) internalize the user's inherent traits and preferences, (2) track how the user profiling and preferences evolve over time, and (3) generate personalized responses accordingly in new scenarios. In this work, we introduce the PERSONAMEM benchmark. PERSONAMEM features curated user profiles with over 180 simulated user-LLM interaction histories, each containing up to 60 sessions of multi-turn conversations across 15 real-world tasks that require personalization. Given an in-situ user query, i.e. query issued by the user from the first-person perspective, we evaluate LLM chatbots' ability to identify the most suitable response according to the current state of the user's profile. We observe that current LLMs still struggle to recognize the dynamic evolution in users' profiles over time through direct prompting approaches. As a consequence, LLMs often fail to deliver responses that align with users' current situations and preferences, with frontier models such as GPT-4.1, o4-mini, GPT-4.5, o1, or Gemini-2.0 achieving only around 50% overall accuracy, suggesting room for improvement. We hope that PERSONAMEM, along with the user profile and conversation simulation pipeline, can facilitate future research in the development of truly user-aware chatbots. Code and data are available at github.com/bowen-upenn/PersonaMem.

cs.CL↗

arXiv2025

Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation

While large language models (LLMs) have been increasingly adopted for machine translation (MT), their performance for specialist domains such as medicine and law remains an open challenge. Prior work has shown that LLMs can be domain-adapted at test-time by retrieving targeted few-shot demonstrations or terminologies for inclusion in the prompt. Meanwhile, for general-purpose LLM MT, recent studies have found some success in generating similarly useful domain knowledge from an LLM itself, prior to translation. Our work studies domain-adapted MT with LLMs through a careful prompting setup, finding that demonstrations consistently outperform terminology, and retrieval consistently outperforms generation. We find that generating demonstrations with weaker models can close the gap with larger model's zero-shot performance. Given the effectiveness of demonstrations, we perform detailed analyses to understand their value. We find that domain-specificity is particularly important, and that the popular multi-domain benchmark is testing adaptation to a particular writing style more so than to a specific domain.

cs.CL↗

arXiv2024

Enhancing Adversarial Resistance in LLMs with Recursion

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance of LLMs to manipulation through the use of prompt simplification techniques. By increasing the transparency of complex and confusing adversarial prompts, the proposed method enables more reliable detection and prevention of malicious inputs. Our findings attempt to address a critical problem in AI safety and security, providing a foundation for the development of systems able to distinguish harmless inputs from prompts containing malicious intent. As LLMs continue to be used in diverse applications, the importance of such safeguards will only grow.

cs.CR↗

arXiv2024

Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness

The paradigm of retrieval-augmented generated (RAG) helps mitigate hallucinations of large language models (LLMs). However, RAG also introduces biases contained within the retrieved documents. These biases can be amplified in scenarios which are multilingual and culturally-sensitive, such as territorial disputes. We thus introduce BordIRLines, a dataset of territorial disputes paired with retrieved Wikipedia documents, across 49 languages. We evaluate the cross-lingual robustness of this RAG setting by formalizing several modes for multilingual retrieval. Our experiments on several LLMs show that incorporating perspectives from diverse languages can in fact improve robustness; retrieving multilingual documents best improves response consistency and decreases geopolitical bias over RAG with purely in-language documents. We also consider how RAG responses utilize presented documents, finding a much wider variance in the linguistic distribution of response citations, when querying in low-resource languages. Our further analyses investigate the various aspects of a cross-lingual RAG pipeline, from retrieval to document contents. We release our benchmark and code to support continued research towards equitable information access across languages at https://huggingface.co/datasets/borderlines/bordirlines.

cs.CL↗

arXiv2024

On the Internal Sum of Puiseux Monoids

In this paper, we investigate the internal (finite) sum of submonoids of rank-$1$ torsion-free abelian groups. These submonoids, when not groups, are isomorphic to nontrivial submonoids of the nonnegative cone of $\mathbb Q$, known as Puiseux monoids, and have been actively studied during the last few years. Here we study how the atomicity and arithmetic of Puiseux monoids behave under their internal (finite) sum inside the abelian group $\mathbb Q$. We study the factorization properties of such internal sums, giving priority to Cohn's notion of atomicity and the classical bounded and finite factorization properties introduced and studied in 1990 by Anderson, Anderson, and Zafrullah in the setting of integral domains, and then generalized by Halter-Koch to commutative monoids. We pay special attention to how each of the considered properties behaves under the internal sum of a Puiseux monoid with a finitely generated Puiseux monoid. Throughout the paper, we also discuss examples showing that our primary results do not hold for submonoids of torsion-free abelian groups with rank larger than $1$.

math.AC↗

arXiv2024

Uncovering Differences in Persuasive Language in Russian versus English Wikipedia

We study how differences in persuasive language across Wikipedia articles, written in either English and Russian, can uncover each culture's distinct perspective on different subjects. We develop a large language model (LLM) powered system to identify instances of persuasive language in multilingual texts. Instead of directly prompting LLMs to detect persuasion, which is subjective and difficult, we propose to reframe the task to instead ask high-level questions (HLQs) which capture different persuasive aspects. Importantly, these HLQs are authored by LLMs themselves. LLMs over-generate a large set of HLQs, which are subsequently filtered to a small set aligned with human labels for the original task. We then apply our approach to a large-scale, bilingual dataset of Wikipedia articles (88K total), using a two-stage identify-then-extract prompting strategy to find instances of persuasion. We quantify the amount of persuasion per article, and explore the differences in persuasion through several experiments on the paired articles. Notably, we generate rankings of articles by persuasion in both languages. These rankings match our intuitions on the culturally-salient subjects; Russian Wikipedia highlights subjects on Ukraine, while English Wikipedia highlights the Middle East. Grouping subjects into larger topics, we find politically-related events contain more persuasion than others. We further demonstrate that HLQs obtain similar performance when posed in either English or Russian. Our methodology enables cross-lingual, cross-cultural understanding at scale, and we release our code, prompts, and data.

cs.CL↗

arXiv2024

Eliciting Better Multilingual Structured Reasoning from LLMs through Code

The development of large language models (LLM) has shown progress on reasoning, though studies have largely considered either English or simple reasoning tasks. To address this, we introduce a multilingual structured reasoning and explanation dataset, termed xSTREET, that covers four tasks across six languages. xSTREET exposes a gap in base LLM performance between English and non-English reasoning tasks. We then propose two methods to remedy this gap, building on the insight that LLMs trained on code are better reasoners. First, at training time, we augment a code dataset with multilingual comments using machine translation while keeping program code as-is. Second, at inference time, we bridge the gap between training and inference by employing a prompt structure that incorporates step-by-step code primitives to derive new facts and find a solution. Our methods show improved multilingual performance on xSTREET, most notably on the scientific commonsense reasoning subtask. Furthermore, the models show no regression on non-reasoning tasks, thus demonstrating our techniques maintain general-purpose abilities.

cs.CL↗

arXiv2023

Large Language Models as Sous Chefs: Revising Recipes with GPT-3

With their remarkably improved text generation and prompting capabilities, large language models can adapt existing written information into forms that are easier to use and understand. In our work, we focus on recipes as an example of complex, diverse, and widely used instructions. We develop a prompt grounded in the original recipe and ingredients list that breaks recipes down into simpler steps. We apply this prompt to recipes from various world cuisines, and experiment with several large language models (LLMs), finding best results with GPT-3.5. We also contribute an Amazon Mechanical Turk task that is carefully designed to reduce fatigue while collecting human judgment of the quality of recipe revisions. We find that annotators usually prefer the revision over the original, demonstrating a promising application of LLMs in serving as digital sous chefs for recipes and beyond. We release our prompt, code, and MTurk template for public use.

cs.CL↗

arXiv2023

This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models

Do the Spratly Islands belong to China, the Philippines, or Vietnam? A pretrained large language model (LLM) may answer differently if asked in the languages of each claimant country: Chinese, Tagalog, or Vietnamese. This contrasts with a multilingual human, who would likely answer consistently. In this paper, we show that LLMs recall certain geographical knowledge inconsistently when queried in different languages -- a phenomenon we term geopolitical bias. As a targeted case study, we consider territorial disputes, an inherently controversial and multilingual task. We introduce BorderLines, a dataset of territorial disputes which covers 251 territories, each associated with a set of multiple-choice questions in the languages of each claimant country (49 languages in total). We also propose a suite of evaluation metrics to precisely quantify bias and consistency in responses across different languages. We then evaluate various multilingual LLMs on our dataset and metrics to probe their internal knowledge and use the proposed metrics to discover numerous inconsistencies in how these models respond in different languages. Finally, we explore several prompt modification strategies, aiming to either amplify or mitigate geopolitical bias, which highlights how brittle LLMs are and how they tailor their responses depending on cues from the interaction context. Our code and data are available at https://github.com/manestay/borderlines

cs.CL↗

arXiv2023

PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale

Existing question answering (QA) systems owe much of their success to large, high-quality training data. Such annotation efforts are costly, and the difficulty compounds in the cross-lingual setting. Therefore, prior cross-lingual QA work has focused on releasing evaluation datasets, and then applying zero-shot methods as baselines. This work proposes a synthetic data generation method for cross-lingual QA which leverages indirect supervision from existing parallel corpora. Our method termed PAXQA (Projecting annotations for cross-lingual (x) QA) decomposes cross-lingual QA into two stages. First, we apply a question generation (QG) model to the English side. Second, we apply annotation projection to translate both the questions and answers. To better translate questions, we propose a novel use of lexically-constrained machine translation, in which constrained entities are extracted from the parallel bitexts. We apply PAXQA to generate cross-lingual QA examples in 4 languages (662K examples total), and perform human evaluation on a subset to create validation and test splits. We then show that models fine-tuned on these datasets outperform prior synthetic data generation models over several extractive QA datasets. The largest performance gains are for directions with non-English questions and English contexts. Ablation studies show that our dataset generation method is relatively robust to noise from automatic word alignments, showing the sufficient quality of our generations. To facilitate follow-up work, we release our code and datasets at https://github.com/manestay/paxqa .

cs.CL↗