# Benchmarking Source-Sensitive Reasoning in Turkish: Humans and LLMs under Evidential Trust Manipulation

arXiv: https://arxiv.org/abs/2604.24665 · HTML: https://mlsanity.com/paper/2604.24665/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 16 of its 64 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [HalluLens: LLM Hallucination Benchmark](https://mlsanity.com/paper/2504.17550/) (2025)
- [AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents](https://mlsanity.com/paper/2601.06818/) (2026)
- [Tokenization Standards for Linguistic Integrity: Turkish as a Benchmark](https://mlsanity.com/paper/2502.07057/) (2025)
- [Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish](https://mlsanity.com/paper/2508.16431/) (2025)
- [Tokens with Meaning: A Hybrid Tokenization Approach for Turkish](https://mlsanity.com/paper/2508.14292/) (2025)
- [Clause-Internal or Clause-External? Testing Turkish Reflexive Binding in Adapted versus Chain of Thought Large Language Models](https://mlsanity.com/paper/2602.00380/) (2026)
- [Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification](https://mlsanity.com/paper/2602.04297/) (2026)
- [Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain](https://mlsanity.com/paper/2601.16018/) (2026)
- [Emotion Recognition for Low-Resource Turkish: Fine-Tuning BERTurk on TREMO and Testing on Xenophobic Political Discourse](https://mlsanity.com/paper/2505.12160/) (2025)
- [Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not](https://mlsanity.com/paper/2604.04825/) (2026)

## Built on by (most cited first, 1 of 1)

- [Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification](https://mlsanity.com/paper/2606.07479/) (2026)

## Abstract (arXiv)

This paper investigates whether source trustworthiness shapes Turkish evidential morphology and whether large language models (LLMs) track this sensitivity. We study the past-domain contrast between -DI and -mIs in controlled cloze contexts where the information source is overtly external, while only its perceived reliability is manipulated (High-Trust vs. Low-Trust). In a human production experiment, native speakers of Turkish show a robust trust effect: High-Trust contexts yield relatively more -DI, whereas Low-Trust contexts yield relatively more -mIs, with the pattern remaining stable across sensitivity analyses. We then evaluate 10 LLMs in three prompting paradigms (open gap-fill, explicit past-tense gap-fill, and forced-choice A/B selection). LLM behavior is highly model- and prompt-dependent: some models show weak or local trust-consistent shifts, but effects are generally unstable, often reversed, and frequently overshadowed by output-compliance problems and strong base-rate suffix preferences. The results provide new evidence for a trust-/commitment-based account of Turkish evidentiality and reveal a clear human-LLM gap in source-sensitive evidential reasoning.