Large language models: open-access research

Journal article

Who Spoke Next Is Not Who Should Have: What Zero-Shot Failure on Multi-Party Turn-Taking Benchmarks Measures, Why the Human Reference Sits Beside the Models, and What Would Show That Knowing When to Speak Must Be Trained

Pranay Mahendrakar 2026

An assistant that joins a group conversation has to decide, at every pause, whether to take the floor. Two 2026 benchmarks report that language models prompted zero-shot make this decision badly and that fine-tuning repairs it, and both conclude that knowing when to speak is learned rather than…

Cite Related research LOR-00111 · 1 view · 1 download

PDF420.3 KB

Journal article

Three Rounds on Emergent Analogy: What the Webb, Hodel-West and Lewis-Mitchell Exchange Settled, How Its Third Round Tested a System While Still Claiming the Model, and Whether 'Counting' Names the Step That Analogy Theory Calls Inference

Pranay Mahendrakar 2026

In 2023 a large language model was reported to solve text-based analogy problems zero-shot at or above the level of college students. They showed that performance on letter-string analogies collapses when the alphabet is permuted or replaced by symbols, while human performance does not. The…

Cite Related research LOR-00070 · 9 views · 23 downloads

PDF439.3 KB

Journal article

Does a Model Forget Differently When the Data Is Its Own? RL's Retention Advantage and Model Collapse Are Claims About the Same Loop, and No Study Has Measured Both

Pranay Mahendrakar 2026

Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy RL is implicitly biased toward…

Cite Related research LOR-00052 · 8 views · 31 downloads

PDF9.3 MB

Journal article

Faithful to What? Four Instruments for Chain-of-Thought Faithfulness Disagree With Each Other, and the One Ground-Truth Check Run So Far Found Most of Them Near Chance

Pranay Mahendrakar 2026

A chain-of-thought (CoT) trace is called "faithful" when it accurately represents the computation that produced the model's answer, as opposed to a plausible-sounding story invented after the fact (Jacovi and Goldberg, 2020). Whether published CoT traces meet this bar is disputed, and the dispute…

Cite Related research LOR-00050 · 26 views · 41 downloads

PDF573.3 KB

Journal article

Poison Below the Base Rate: What the Near-Constant Poisoning Result Establishes About Detection, and Four Things It Does Not

Pranay M. Mahendrakar 2026

A widely cited 2025 result reports that backdooring a language model through its training data takes a near-constant number of poisoned documents rather than a constant fraction of the corpus, and the field has read that as retiring the proportion-based threat model that most poison detectors are…

Cite Related research LOR-00036 · 6 views · 7 downloads

PDF441.6 KB

Journal article

The Crossover Does Not Carry the Claim: Pass@k Inversion, the Reasoning Boundary, and Five Premises the RLVR Debate Leaves Unstated

Pranay M. Mahendrakar 2026

A model trained with reinforcement learning from verifiable rewards beats its base model at one sample and loses to it at many. The field has read that crossover as a measurement of the reasoning boundary and has spent two years arguing about which direction the boundary moved. This paper…

Cite Related research LOR-00072 · 7 views · 9 downloads

PDF461 KB

Journal article

The Crossover Does Not Carry the Claim: Pass@k Inversion, the Reasoning Boundary, and Five Premises the RLVR Debate Leaves Unstated

Pranay M. Mahendrakar 2026

A model trained with reinforcement learning from verifiable rewards beats its base model at one sample and loses to it at many. The field has read that crossover as a measurement of the reasoning boundary and has spent two years arguing about which direction the boundary moved. This paper…

Cite Related research LOR-00034 · 6 views · 29 downloads

PDF457.3 KB

Journal article

The Self-Verification Gap: Why Working Hallucination Detectors Are External, and What Real-Time Correction Would Actually Require

Pranay M. Mahendrakar 2026

Large language models generate fluent text that is sometimes false, and a substantial literature now proposes to have the model notice and repair those errors while it writes. Semantic entropy detects confabulations across datasets and tasks without prior knowledge of the task (Farquhar et al…

Cite Related research LOR-00041 · 9 views · 37 downloads

PDF541.9 KB

8 records