5The Batch (DeepLearning.AI)·
Stanford/Together AI study finds retrieval is the weakest link for LLM web-search agents
Researchers at Stanford University and Together AI tested six LLMs equipped with web-search tools on daily news questions across six languages, finding that retrieval failures account for the majority of errors (38.8%) rather than reasoning or comprehension failures. Top models exceeded 90% accuracy on well-formed English multiple-choice questions, but performance degraded significantly for Hindi, free-response formats, and questions containing false premises. The study identifies three retrieval improvement levers—indexing coverage, source ranking, and multilingual query handling—and suggests retrieval optimization may yield larger gains than model scaling for time-sensitive queries.
Related guides (5)
Anthropic
Anthropic: Frontier AI Lab at the Intersection of Capability and Safety Governance
Read asIn-depth
Related events (8)
Study of security and privacy prompts in the wild reveals LLM response quality gaps and inconsistency
Researchers analyzed 14,727 security and privacy (S&P) prompts drawn from WildChat's 3.2M real user-LLM conversations, categorizing them into nine topic areas and evaluating response quality across 270 advice-seeking prompts. Commercial models substantially outperformed open-weight models (GPT achieving 98% 'good enough' responses vs. Llama 4 at 47%), but even high-performing commercial models showed inconsistent responses across repeated runs of the same prompt. The study is the first to analyze real user S&P queries to LLMs rather than expert-authored test sets, surfacing both a capability gap and a reliability concern.
RL-trained LLMs learn retriever-specific query formulation strategies for RAG
A new arXiv paper presents the first systematic study of using reinforcement learning to teach LLMs to adapt query formulation strategies to different retrieval backends. The authors find that different retrievers have surprisingly distinct optimal query styles (e.g., descriptive vs. question-like), making cross-retriever strategy transfer ineffective. They introduce a branching-based rollout technique to stabilize training over multi-step retrieval trajectories and show gains from retriever-specific human guidance and model scaling.
Benchmarking study finds LLMs fail at counterintuitive probability problems despite strong standard performance
A new arXiv paper evaluates 8 state-of-the-art LLMs on discrete probability problems using two datasets: standard exercises (average accuracy 0.96) and counterintuitive exercises designed to trigger heuristic reasoning (average accuracy 0.59). The authors document token bias causing 20%+ performance drops when canonical problem formulations are disguised, and up to 34% degradation when misleading suggestions are embedded in prompts. The findings argue that current LLMs are not genuine probabilistic reasoners despite their success on advanced math benchmarks.
Systematic 14-Day Evaluation of Six AI Chatbots as News Intermediaries Across Languages and Regions
Researchers evaluated six commercial AI chatbots (Gemini 3 Flash/Pro, Grok 4, Claude 4.5 Sonnet, GPT-5, GPT-4o mini) on 2,100 factual questions derived from same-day BBC News reporting across six regional services over 14 days in February 2026. Top systems exceed 90% multiple-choice accuracy on breaking news but lose 11-17% under free-response conditions. Key findings include systematic Hindi-language underperformance (79% vs. 89-91% elsewhere) driven by Anglophone retrieval bias, retrieval failures accounting for over 70% of errors, and dramatic accuracy collapse (to 19-70%) on questions containing subtle false premises. A detection-accuracy paradox is identified: the best false-premise detector does not yield the best adversarial accuracy, suggesting premise detection and answer recovery are partially independent capabilities.
Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study
This paper systematically investigates strategies for extending LLM-based automatic evaluation (LLMs-as-a-Judge) to multilingual settings, covering high-, mid-, and low-resource languages (English, Spanish, Basque). The authors compare instruction translation, monolingual vs. multilingual supervision, and model size, finding that fine-tuned smaller models can match proprietary models when in-domain data is available, while zero-shot larger models are preferable out-of-domain. Two meta-evaluation datasets are extended to Spanish and Basque, and all data and code are publicly released.
Tracing the Emergence of Human-Like Pragmatic Reasoning in LLMs Across Languages
Researchers conducted a population-matching experiment evaluating 25 LLMs on conditional inference tasks across four languages, comparing model behavior to matched human populations. The study finds that LLMs function as accurate semantic operators but systematically fail to capture pragmatic enrichments—context-sensitive inferences beyond literal logical meaning—that humans apply effortlessly. Model performance on pragmatic reasoning is not predicted by open vs. closed weights, training orientation, or architecture type, suggesting pragmatic reasoning remains an emergent and unreliable capability. The findings contribute to ongoing debates about whether LLMs reason like humans or merely approximate surface-level linguistic patterns.
Systematic evaluation of LLM prompt sensitivity in healthcare settings reveals safety risks
Researchers conduct a sensitivity analysis of both general-purpose and medical-specific LLMs using the MedMCQA benchmark, testing robustness to lexical and syntactic prompt perturbations. The study finds that even minor phrasing changes can alter clinical advice, and adversarial prompts can produce dangerous outputs such as incorrect dosages or omitted critical findings. Both general-purpose models (GPT-3.5, Llama 3) and domain-specific models (ClinicalBERT, BioLlama3, BioBERT) exhibit this fragility, with syntactic reordering and misleading contextual cues proving more destabilizing than simple paraphrasing.
Cross-lingual prompting strategies unlock hidden parametric knowledge in LLMs
A new arXiv preprint investigates how cross-lingual prompting can surface factual knowledge that standard inference techniques fail to retrieve in multilingual LLMs. The authors identify four dimensions of cross-lingual exploration governing parametric knowledge retrieval and evaluate them on multilingual factual benchmarks across 17 typologically diverse languages. Results show cross-lingual exploration improves both factual recall and cross-lingual consistency, and is claimed to be a more compute-efficient approach than scaling native-language inference.