arXiv AI
Jun 24
CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression
arXiv:2606. 24083v1 Announce Type: cross Abstract: "Talk short.
Structured Output Collapses Answer Diversity Across 44 Language Models
arXiv:2607. 18476v1 Announce Type: cross Abstract: When a language model must choose one answer from a large space of equally valid options, a format clause -- "Reply with JSON only" -- changes which answer it chooses.
Related stories
arXiv AI
Jul 15
The One-Word Census: Answer-Choice Conformity Across 44 Language Models
arXiv:2607. 12796v1 Announce Type: cross Abstract: When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer every other model picks?
arXiv AI
Jul 24
PhantomFill: When the Form Demands an Answer, Language Models Invent One
arXiv:2607. 20492v1 Announce Type: cross Abstract: Language models in production do not write prose.
arXiv AI
Jul 22
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
Hugging Face Trending Papers
Jul 14
The One-Word Census: Answer-Choice Conformity Across 44 Language Models
When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer every other model picks? Asked to "pick a word -- any word," 44 models chose "serendipity" 41% of the time.
arXiv AI
Jun 9
Capacity, Not Format: Rethinking Structured Reasoning Failures
arXiv:2606. 09410v1 Announce Type: new Abstract: Prior work treats structured output as a reasoning tax, but this framing is incomplete: the cost of formatting depends strongly on a model's spare capacity.
arXiv AI
Jul 7
Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)
arXiv:2607. 04223v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why.
arXiv AI
Jul 7
They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It
arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
arXiv AI
Jun 15
Verbatim Chunks Beat Extracted Artifacts: A Controlled Ablation of Memory Representations for Long LLM Conversations
arXiv:2601. 00821v3 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts -- extracted facts, decisions, or events -- on the premise that distilled structure retrieves better than raw text.
arXiv AI
Jul 28
Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models
arXiv:2607. 23976v1 Announce Type: cross Abstract: Appending a two-word confirmation tag to a decision question -- "Is X the better choice?
Hugging Face Trending Papers
Jul 21
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models.
arXiv Machine Learning
Jun 2
Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
arXiv:2606. 01456v1 Announce Type: new Abstract: Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sales assistants for purchases, negotiation agents for concessions.