arXiv subjects

Katharina von der Wense

Publications and source records attributed to Katharina von der Wense.

At least 19 recordsLinked to original sources

arXiv2026

Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation

Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It has been shown that forcing a model to reason in another language degrades accuracy, even when the reasoning language matches the language of the prompt -- but only for a setting where the model reasons over a short prompt. Here, we ask whether the same holds for retrieval-augmented generation (RAG), where the model must read and integrate a large amount of retrieved evidence in the target language. To study this, we build a fully monolingual German RAG question-answering testbed over the fictional world of the tabletop role-playing game The Dark Eye, a domain that is richly documented in German but too niche for the model to answer from memory, so that it has to rely on retrieval. Varying the forced reasoning language of an agentic RAG system on this testbed, we find that aligning the reasoning language with the language of the query and the retrieved documents helps. Forced German reasoning outperforms forced French, although the model benchmarks higher in French, so the benefit comes from alignment and not from language proficiency. The advantage grows when the retrieved context is richer and structure-aware. However, forced German only reaches the level of the model's native, unconstrained English reasoning without surpassing it, showing that native multilingual reasoning is needed. We publicly release the testbed and QA benchmark.

cs.CL↗

arXiv2026

Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation

Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked factor: the hidden injection of the current date into system prompts, which users cannot control and which changes every day. Across 9 recent LLMs and 6 datasets spanning multiple-choice QA (MCQA), math reasoning, code generation, and machine translation, performance varies solely with the current date, with deltas of up to 6% on MCQA, 14% on math reasoning, 7% on code generation, and 2.84 BLEU on machine translation. Model rankings also shift, affecting leaderboards. This date effect exceeds other sources of non-determinism, such as batch size and numerical precision. Standard prompting techniques -- chain-of-thought and few-shot prompting -- do not reduce the sensitivity; chain-of-thought even amplifies it. Our findings underscore the need for careful evaluation protocols to ensure reproducibility and fair comparisons in LLM research.

cs.CL↗

arXiv2026

Calibration as a First-Class Criterion in LLM Evaluation

Calibration of language models -- the alignment between expressed or implicit confidence and empirical correctness -- is a well-studied subfield within NLP. Methods to measure it already exist. The problem is adoption: outside this subfield, NLP research regularly introduces new models, datasets, and benchmarks without checking whether the model's confidence scores are meaningful. We argue that this adoption gap is a major obstacle to trustworthy LLM evaluation. Miscalibration causes problems in two distinct areas: at deployment, where overconfident mistakes cause real harm, and inside the research pipeline, where methods like LLM-as-a-judge, synthetic data generation, and active learning rely on calibrated confidence without verifying it. Standard calibration metrics only require two inputs per example: a confidence score and a correctness judgment. Most benchmarks in use today already provide both, meaning calibration can be reported immediately. For open-ended generation, however, defining these two inputs is still an open challenge. We argue that each NLP subfield should pair its main performance metric with a calibration score and call for treating calibration as an essential property of every model rather than a niche topic.

cs.CL↗

arXiv2026

Perspectives on Cross-Lingual Consistency in LLMs for Medical Questions

Should multilingual LLMs answer medical questions consistently across input languages, or adapt responses to cultural cues? Existing multilingual medical benchmarks usually assume that medically correct answers should remain consistent across languages and treat cross-lingual variation as model error. In contrast, cultural adaptation research argues that appropriate medical answers may legitimately differ across contexts. We review the multilingual medical NLP literature through these two perspectives, we identify three gaps: limited stakeholder perspectives (e.g., of medical professionals), a lack of empirical evidence on which approach better serves users, and no benchmarks capable of distinguishing universally correct from culture-specific cases. To address the first gap, we survey 356 participants across three stakeholder groups (medical, NLP, and anthropology professionals) in three countries (Germany, Spain, and the United States). Anthropologists consistently favor adaptation, while medical and NLP respondents remain divided, with notable divergence between U.S. and European medical professionals. LLMs prompted with profession and country personas fail to reproduce this variation, overestimating cross-lingual consistency preference among NLP and medical personas. We conclude that neither consistency nor adaptation can currently be considered clearly preferable, highlighting the need for empirical evidence on which approach better serves users across cultural contexts.

cs.CL↗

arXiv2026

An Investigation of Translationese in the Generations of Multilingual Large Language Models

Text which has been translated from another language tends to carry with it evidence of translation$\unicode{x2014}$hence, it is often referred to as $\textit{translationese}$. Multilingual large language models (MLLMs) generate text in a variety of languages. However, it is still unclear if MLLMs' generations resemble internal translation (from English or, potentially, other languages) and, thus, result in translationese. Here, we ask the following research questions: (1) Does text generated by MLLMs resemble translationese? (2) How does translationese produced by MLLMs differ from translationese produced through direct translation? We leverage established indicators of translated text to evaluate text generated by state-of-the-art MLLMs in five languages, comparing to both non-translated and human-written baselines in order to isolate translationese from other kinds of interference. Through the use of high-accuracy classification models, analyses of variance on individual linguistic features, and the collection of human annotations in a subset of two languages (German and Spanish), we assess the translationese content of MLLM generations and examine the key features that distinguish MLLM-generated text from typical translation-related interference.

cs.CL↗

arXiv2026

Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation

The rapid rise in popularity of large language models (LLMs) for translation calls for a thorough study of the reliability of their confidence in their own outputs. Unlike many generation tasks, translation errors and confidence levels can be useful at different levels of granularity (tokens, words, or spans). Unsupervised approaches based on internal signals like predicted probabilities can be misleading because they reflect certainty among alternatives rather than correctness. In addition, they require access to such internal signals. Here, we devise five verbalized methods of extracting an LLM's per-token confidence without those shortcomings and compare their reliability with that of the model's internal signals of certainty. We evaluate reliability using two forms of alignment: fine-grained error detection and calibration. For both, internal and verbalized methods perform similarly, although results vary by model. Interestingly, we find little to no correlation between internal and verbalized methods.

cs.CL↗

arXiv2026

Large Language Models Are Overconfident in Their Own Responses

Prior work has shown that instruction-tuned large language models (LLMs) are less well calibrated than their base pre-trained counterparts. However, little is known about the frequently used chat template's effect on the calibration of conversational LLMs. In this work, we investigate the mechanisms driving this miscalibration by decoupling the effects of the post-training algorithm and the chat format. We find that, while instruction tuning fundamentally harms calibration, the chat template aggravates the issue through an "ownership bias" -- models are significantly more confident in their own answers than in identical answers provided by a user. Extensive experiments across six recent open-weight LLMs, three benchmarks, and three confidence elicitation methods show that models assign up to 26% higher confidence to their own responses. Leveraging this insight, we propose a simple inference-time strategy: framing the model's answer as user input during confidence elicitation. This approach significantly reduces overconfidence and improves calibration by up to 26% without the need for retraining, narrowing the gap between base and instruction-tuned models.

cs.CL↗

arXiv2026

From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation

Prior work evaluates code generation bias primarily through simple conditional statements, which represent only a narrow slice of real-world programming and reveal solely overt, explicitly encoded bias. We demonstrate that this approach dramatically underestimates bias in practice by examining a more realistic task: generating machine learning (ML) pipelines. Testing both code-specialized and general-instruction large language models, we find that generated pipelines exhibit significant bias during feature selection. Sensitive attributes appear in 87.7% of cases on average, despite models demonstrably excluding irrelevant features (e.g., including "race" while dropping "favorite color" for credit scoring). This bias is substantially more prevalent than that captured by conditional statements, where sensitive attributes appear in only 59.2% of cases. These findings are robust across prompt mitigation strategies, varying numbers of attributes, and different pipeline difficulty levels. Our results challenge simple conditionals as valid proxies for bias evaluation and suggest current benchmarks underestimate bias risk in practical deployments.

cs.CL↗

arXiv2026

Greater accessibility can amplify discrimination in generative AI

Hundreds of millions of people rely on large language models (LLMs) for education, work, and even healthcare. Yet these models are known to reproduce and amplify social biases present in their training data. Moreover, text-based interfaces remain a barrier for many, for example, users with limited literacy, motor impairments, or mobile-only devices. Voice interaction promises to expand accessibility, but unlike text, speech carries identity cues that users cannot easily mask, raising concerns about whether accessibility gains may come at the cost of equitable treatment. Here we show that audio-enabled LLMs exhibit systematic gender discrimination, shifting responses toward gender-stereotyped adjectives and occupations solely on the basis of speaker voice, and amplifying bias beyond that observed in text-based interaction. Thus, voice interfaces do not merely extend text models to a new modality but introduce distinct bias mechanisms tied to paralinguistic cues. Complementary survey evidence ($n=1,000$) shows that infrequent chatbot users are most hesitant to undisclosed attribute inference and most likely to disengage when such practices are revealed. To demonstrate a potential mitigation strategy, we show that pitch manipulation can systematically regulate gender-discriminatory outputs. Overall, our findings reveal a critical tension in AI development: efforts to expand accessibility through voice interfaces simultaneously create new pathways for discrimination, demanding that fairness and accessibility be addressed in tandem.

cs.CL↗

arXiv2026

Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect

Meenzerisch, the dialect spoken in the German city of Mainz, is also the traditional language of the Mainz carnival, a yearly celebration well known throughout Germany. However, Meenzerisch is on the verge of dying out-a fate it shares with many other German dialects. Natural language processing (NLP) has the potential to help with the preservation and revival efforts of languages and dialects. However, so far no NLP research has looked at Meenzerisch. This work presents the first research in the field of NLP that is explicitly focused on the dialect of Mainz. We introduce a digital dictionary-an NLP-ready dataset derived from an existing resource (Schramm, 1966)-to support researchers in modeling and benchmarking the language. It contains 2,351 words in the dialect paired with their meanings described in Standard German. We then use this dataset to answer the following research questions: (1) Can state-of-the-art large language models (LLMs) generate definitions for dialect words? (2) Can LLMs generate words in Meenzerisch, given their definitions? Our experiments show that LLMs can do neither: the best model for definitions reaches only 6.27% accuracy and the best word generation model's accuracy is 1.51%. We then conduct two additional experiments in order to see if accuracy is improved by few-shot learning and by extracting rules from the training set, which are then passed to the LLM. While those approaches are able to improve the results, accuracy remains below 10%. This highlights that additional resources and an intensification of research efforts focused on German dialects are desperately needed.

cs.CL↗

arXiv2025

NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation

This paper presents JGU Mainz's winning system for the BLP-2025 Shared Task on Code Generation from Bangla Instructions. We propose a multi-agent-based pipeline. First, a code-generation agent produces an initial solution from the input instruction. The candidate program is then executed against the provided unit tests (pytest-style, assert-based). Only the failing cases are forwarded to a debugger agent, which reruns the tests, extracts error traces, and, conditioning on the error messages, the current program, and the relevant test cases, generates a revised solution. Using this approach, our submission achieved first place in the shared task with a $Pass@1$ score of 95.4. We also make our code public.

cs.CL↗

arXiv2025

Mitigating Label Length Bias in Large Language Models

Large language models (LLMs) are powerful zero- and few-shot learners. However, when predicting over a set of candidate options, LLMs suffer from label biases, and existing calibration methods overlook biases arising from multi-token class labels. We tackle an issue we call label length bias, where labels of different lengths are treated inconsistently, even after standard length normalization. To mitigate it, we propose normalized contextual calibration (NCC), an effective method that normalizes and calibrates predictions at the full-label level. NCC achieves statistically significant improvements over prior approaches across multiple datasets and models, with gains of up to 10% F1. Moreover, NCC extends bias mitigation to broader tasks such as multiple-choice question answering. Our analysis shows that, when combined with in-context learning, NCC is less sensitive to few-shot example selection, requires fewer examples for competitive performance, and produces more reliable confidence estimates. These findings highlight the importance of mitigating full-label biases to improve the performance and robustness of LLM-based methods, particularly in real-world applications where class labels naturally consist of multiple tokens.

cs.CL↗

arXiv2025

Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer

We present NN-Rank, an algorithm for ranking source languages for cross-lingual transfer, which leverages hidden representations from multilingual models and unlabeled target-language data. We experiment with two pretrained multilingual models and two tasks: part-of-speech tagging (POS) and named entity recognition (NER). We consider 51 source languages and evaluate on 56 and 72 target languages for POS and NER, respectively. When using in-domain data, NN-Rank beats state-of-the-art baselines that leverage lexical and linguistic features, with average improvements of up to 35.56 NDCG for POS and 18.14 NDCG for NER. As prior approaches can fall back to language-level features if target language data is not available, we show that NN-Rank remains competitive using only the Bible, an out-of-domain corpus available for a large number of languages. Ablations on the amount of unlabeled target data show that, for subsets consisting of as few as 25 examples, NN-Rank produces high-quality rankings which achieve 92.8% of the NDCG achieved using all available target data for ranking.

cs.CL↗

arXiv2025

JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA

This paper presents the JGU Mainz submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: Machine Translation and Question Answering, focusing on Ukrainian, Upper Sorbian, and Lower Sorbian. For each language, we jointly fine-tune a Qwen2.5-3B-Instruct model for both tasks with parameter-efficient finetuning. Our pipeline integrates additional translation and multiple-choice question answering (QA) data. For Ukrainian QA, we further use retrieval-augmented generation. We also apply ensembling for QA in Upper and Lower Sorbian. Experiments show that our models outperform the baseline on both tasks.

cs.CL↗

arXiv2025

Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation

Computational morphology has the potential to support language documentation through tasks like morphological segmentation and the generation of Interlinear Glossed Text (IGT). However, our research outputs have seen limited use in real-world language documentation settings. This position paper situates the disconnect between computational morphology and language documentation within a broader misalignment between research and practice in NLP and argues that the field risks becoming decontextualized and ineffectual without systematic integration of User-Centered Design (UCD). To demonstrate how principles from UCD can reshape the research agenda, we present a case study of GlossLM, a state-of-the-art multilingual IGT generation model. Through a small-scale user study with three documentary linguists, we find that despite strong metric based performance, the system fails to meet core usability needs in real documentation contexts. These insights raise new research questions around model constraints, label standardization, segmentation, and personalization. We argue that centering users not only produces more effective tools, but surfaces richer, more relevant research directions

cs.CL↗

arXiv2025

Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

When evaluating large language models (LLMs) with multiple-choice question answering (MCQA), it is common to end the prompt with the string "Answer:" to facilitate automated answer extraction via next-token probabilities. However, there is no consensus on how to tokenize the space following the colon, often overlooked as a trivial choice. In this paper, we uncover accuracy differences of up to 11% due to this (seemingly irrelevant) tokenization variation as well as reshuffled model rankings, raising concerns about the reliability of LLM comparisons in prior work. Surprisingly, we are able to recommend one specific strategy -- tokenizing the space together with the answer letter -- as we observe consistent and statistically significant performance improvements. Additionally, it improves model calibration, enhancing the reliability of the model's confidence estimates. Our findings underscore the importance of careful evaluation design and highlight the need for standardized, transparent evaluation protocols to ensure reliable and comparable results.

cs.CL↗

arXiv2025

Large Language Models Discriminate Against Speakers of German Dialects

Dialects represent a significant component of human culture and are found across all regions of the world. In Germany, more than 40% of the population speaks a regional dialect (Adler and Hansen, 2022). However, despite cultural importance, individuals speaking dialects often face negative societal stereotypes. We examine whether such stereotypes are mirrored by large language models (LLMs). We draw on the sociolinguistic literature on dialect perception to analyze traits commonly associated with dialect speakers. Based on these traits, we assess the dialect naming bias and dialect usage bias expressed by LLMs in two tasks: an association task and a decision task. To assess a model's dialect usage bias, we construct a novel evaluation corpus that pairs sentences from seven regional German dialects (e.g., Alemannic and Bavarian) with their standard German counterparts. We find that: (1) in the association task, all evaluated LLMs exhibit significant dialect naming and dialect usage bias against German dialect speakers, reflected in negative adjective associations; (2) all models reproduce these dialect naming and dialect usage biases in their decision making; and (3) contrary to prior work showing minimal bias with explicit demographic mentions, we find that explicitly labeling linguistic demographics--German dialect speakers--amplifies bias more than implicit cues like dialect usage.

cs.CL↗

arXiv2025

Improving Low-Resource Morphological Inflection via Self-Supervised Objectives

Self-supervised objectives have driven major advances in NLP by leveraging large-scale unlabeled data, but such resources are scarce for many of the world's languages. Surprisingly, they have not been explored much for character-level tasks, where smaller amounts of data have the potential to be beneficial. We investigate the effectiveness of self-supervised auxiliary tasks for morphological inflection -- a character-level task highly relevant for language documentation -- in extremely low-resource settings, training encoder-decoder transformers for 19 languages and 13 auxiliary objectives. Autoencoding yields the best performance when unlabeled data is very limited, while character masked language modeling (CMLM) becomes more effective as data availability increases. Though objectives with stronger inductive biases influence model predictions intuitively, they rarely outperform standard CMLM. However, sampling masks based on known morpheme boundaries consistently improves performance, highlighting a promising direction for low-resource morphological modeling.

cs.CL↗