Related papers: RORA: Robust Free-Text Rationale Evaluation

Large reasoning models (LRMs) sometimes note in their chain of thought (CoT) that they may be under evaluation. Researchers worry that this verbalised evaluation awareness (VEA) causes models to adapt their outputs strategically, optimising…

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason…

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

We conduct a systematic audit of three widely used reasoning benchmarks, SocialIQa, FauxPas-EAI, and ToMi, and uncover pervasive flaws in both benchmark items and evaluation methodology. Using five LLMs (GPT-{3, 3.5, 4, o1}, and LLaMA 3.1)…

Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs). However, the limited expressive capacity of LoRA, stemming from the low-rank constraint, has been recognized as a…

To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for making a prediction. However, an open question is how well these explanations accurately reflect a…

Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reasoning used to produce it. This highlights a fundamental…

Despite the widespread use of LLMs due to their superior performance in various tasks, their high computational costs often lead potential users to opt for the pretraining-finetuning pipeline. However, biases prevalent in manually…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensions improve upon vanilla RLVR (e.g., GRPO) by providing…

Despite its real-world significance, model performance on tabular data remains underexplored, leaving uncertainty about which model to rely on and which prompt configuration to adopt. To address this gap, we create ToRR, a benchmark for…

Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a…

Reranking documents based on their relevance to a given query is a critical task in information retrieval. Traditional reranking methods often lack transparency and rely on proprietary models, hindering reproducibility and interpretability.…

The advent of complex, interconnected long-horizon LLM systems has made it incredibly tricky to identify where and when these systems break down. Evaluation capabilities that currently exist today are limited in that they often focus on…

Evaluating the quality of reasoning traces from large language models remains understudied, labor-intensive, and unreliable: current practice relies on expert rubrics, manual annotation, and slow pairwise judgments. Automated efforts are…

The zero-shot capability of Large Language Models (LLMs) has enabled highly flexible, reference-free metrics for various tasks, making LLM evaluators common tools in NLP. However, the robustness of these LLM evaluators remains relatively…

Figurative language (e.g., irony, hyperbole, understatement) is ubiquitous in human communication, resulting in utterances where the literal and the intended meanings do not match. The Rational Speech Act (RSA) framework, which explicitly…

With software systems becoming increasingly pervasive and autonomous, our ability to test for their quality is severely challenged. Many systems are called to operate in uncertain and highly-changing environment, not rarely required to make…

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Large reasoning models (LRMs) have demonstrated impressive capabilities in domains like mathematics and program synthesis. Despite their strong performance, LRMs often exhibit overthinking -- excessive and redundant reasoning steps that…

Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they…