LLM Evaluations and Benchmarks

Related topics:

• 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
  Therefore, several replication studies have explored strategies for efficiently creating training datasets by leveraging open-source data and powerful models. In this subsection, we introduce the data…
• A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions
  We tested GPT-3.5, GPT-4o, Gemini 1.5 Pro, Claude 3 Opus, Llama 3- 8B, and Llama 3–70B, on the chain-of-thought, EmotionPrompting, ExpertPrompting, Sandbagging, as well as Re-Reading prompt engineerin…
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
  Moreover, we find that ChatGPT is 63.41% accurate on average in 10 different reasoning categories under logical reasoning, non-textual reasoning, and commonsense reasoning, hence making it an unreliab…
• A Survey of Calibration Process for Black-Box LLMs
  In recent years, Confidence Estimation and Calibration have frequently been discussed together, as the estimation of confidence is often influenced by the uncertainty in the model or data, and calibra…
• A Survey on Large Language Models with some Insights on their Capabilities and Limitations
  The rapid advancement of artificial intelligence, particularly with the development of Large Language Models (LLMs) built on the transformer architecture, has redefined the capabilities of natural lan…
• A Systematic Review on the Evaluation of Large Language Models in Theory of Mind Tasks
  This systematic review synthesizes current efforts to assess LLMs’ ability to perform ToM tasks—an essential aspect of human cognition involving the attribution of mental states to oneself and others.…
• Argument Summarization and its Evaluation in the Era of Large Language Models
  Large Language Models (LLMs) have revolutionized various Natural Language Generation (NLG) tasks, including Argument Summarization (ArgSum), a key subfield of Argument Mining (AM). This paper investig…
• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
  Large language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to similar o…
• Assessing adaptive world models in machines with novel games
  Human intelligence exhibits a remarkable capacity for rapid adaptation and effective problem-solving in novel and unfamiliar contexts. We argue that this profound adaptability is fundamentally linked …
• Assessment of Personality Dimensions Across Situations Using Conversational Speech
  Abstract—Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in automatic personality perception (APP), which aims to …
• Auditing language models for hidden objectives
  We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pip…
• AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
  Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed…
• Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration
  While AI agents show potential in scientific ideation, most existing frameworks rely on single-agent refinement, limiting creativity due to bounded knowledge and perspective. Inspired by real-world re…
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
  Large Language Models (LLMs) have been widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness a critical concern. The potential for intentional deception, wher…
• Beyond the Surface: Probing the Ideological Depth of Large Language Models
  Large Language Models (LLMs) have demonstrated pronounced ideological leanings, yet the stability and depth of these positions remain poorly understood. Surface-level responses can often be manipulate…
• CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions
  Existing benchmarks fall short in realism, data fidelity, agent-user interaction, and coverage across business scenarios and industries. To address these gaps, we introduce CRMArena-Pro, a novel bench…
• Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge
  Large Language Models (LLMs) have become increasingly powerful and ubiquitous, but their stochastic nature poses challenges to the reliability of their outputs. While deterministic settings can improv…
• Comparing Human and AI Therapists in Behavioral Activation for Depression: Cross-Sectional Questionnaire Study
  A shortage of trained therapists and mental health care providers has driven informal use of LLMs for therapeutic support. However, their clinical utility remains poorly defined. Objective: This study…
• Complex Logical Instruction Generation
  Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agentic behaviors. As tas…
• DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
  Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most existing frameworks …
• Development and validation of large language model rating scales for automatically transcribed psychological therapy sessions
  Rating scales have shaped psychological research, but are resource-intensive and can burden participants. Large Language Models (LLMs) offer a tool to assess latent constructs in text. This study intr…
• Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
  Large language models (LLMs) are trained to imitate humans to explain human decisions. However, do LLMs explain themselves? Can they help humans build mental models of how LLMs process different input…
• Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust
  As large language models (LLMs) are increasingly studied as role-playing agents to generate synthetic data for human behavioral research, ensuring that their outputs remain coherent with their assigne…
• Evaluating Large Language Models at Evaluating Instruction Following
  As research in large language models (LLMs) continues to accelerate, LLM-based evaluation has emerged as a scalable and cost-effective alternative to human evaluations for comparing the ever increasin…
• Evaluating Large Language Models in Theory of Mind Tasks
  Many animals excel at using cues such as vocalization, body posture, gaze, or facial expression to predict other animals’ behavior and mental states. Dogs, for example, can easily distinguish between …
• Evaluation and Benchmarking of LLM Agents: A Survey
  The rise of LLM-based agents has opened new frontiers in AI applications, yet evaluating these agents remains a complex and underdeveloped area. This survey provides an in-depth overview of the emergi…
• Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks
  Abstract—Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rat…
• Exploring Student-AI Interactions in Vibe Coding
  Findings. For both groups, the majority of student interactions with Replit were to test or debug the prototype and only rarely did students visit code. Prompts by advanced software engineering studen…
• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
  evaluating the alignment of LLMs to human values is challenging for two reasons. First, open-ended user instructions usually require a composition of multiple abilities, which makes measurement with a…
• Faith and Fate: Limits of Transformers on Compositionality
  In an attempt to demystify transformer LLMs, we investigate the limits of these models across three representative compositional tasks—multi-digit multiplication, logic grid puzzles, and a classic dyn…
• FormulaOne: Measuring the Depth of Algorithmic Reasoning Beyond Competitive Programming
  Frontier AI models demonstrate formidable breadth of knowledge. But how close are they to true human — or superhuman — expertise? Genuine experts can tackle the hardest problems and push the boundarie…
• From Human to Machine Psychology: A Conceptual Framework for Understanding Well-Being in Large Language Models
  As large language models (LLMs) increasingly simulate human cognition and behavior, researchers have begun to investigate their psychological properties. Yet, what it means for such models to flourish…
• GPT-4 is judged more human than humans in displaced and inverted Turing tests
  In many cases, people will not interact directly with AI systems but instead read conversations between AI systems and other people. We measured how well people and large language models can discrimin…
• Gdpval: Evaluating Ai Model Performance On Real-world Economically Valuable Tasks
  To grade the 220 open-sourced gold subset, we conducted blinded expert pairwise comparisons, where experts in the relevant occupation were presented with a request and reference files and asked to ran…
• Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?
  Coaxing out desired behavior from pretrained models, while avoiding undesirable ones, has redefined NLP and is reshaping how we interact with computers. What was once a scientific engineering discipli…
• How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
  Most traditional AI safety research views models as machines and centers on algorithm focused attacks developed by security experts. As large language models (LLMs) become increasingly common and comp…
• IFEvalCode: Controlled Code Generation
  Code large language models (Code LLMs) have achieved significant advancements in various code-related tasks, particularly in code generation, where the code LLMs produce the target code from natural l…
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
  Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we…
• Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains
  However, the quality and transparency of their internal reasoning processes remain underexplored. This work moves beyond the final-answer accuracy and investigates step-by-step reasoning in the medica…
• KoLA: Carefully Benchmarking World Knowledge of Large Language Models
  Given the importance of world knowledge to LLMs, we construct a Knowledge-oriented LLM Assessment benchmark (KoLA), in which we carefully design three crucial factors: (1) For ability modeling, we mim…
• LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools
  With LLMCHECKUP, we present an easily accessible tool that allows users to chat with any state-of-the-art large language model (LLM) about its behavior. We enable LLMs to generate all explanations by …
• LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
  Trustworthy evaluations of dangerous capabilities are increasingly crucial for determining whether an AI system is safe to deploy. One empirically demonstrated threat to this is sandbagging — the stra…
• Language Models Learn to Mislead Humans via RLHF
  Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve h…
• Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What d…
• Large language models surpass human experts in predicting neuroscience results
  Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offer a solution. LLMs t…
• LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries
  Tool calling has emerged as a critical capability for AI agents to interact with the real world and solve complex tasks. While the Model Context Protocol (MCP) provides a powerful standardized framewo…
• LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
  We conduct detailed analysis with a range of LLMs such as GPT-4, ChatGPT, Gemini, Llama-2, and Mistral using chain-of-thought prompting. Experimental results show that existing LLMs do not fare well o…
• Logical Reasoning in Large Language Models: A Survey
  With the emergence of advanced reasoning models like OpenAI o3 and DeepSeek-R1, large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, their ability to perform rigo…
• Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
  Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in re…
• Measuring Human Preferences in RLHF is a Social Science Problem
  RLHF assumes that annotation responses reflect genuine human preferences. We argue this assumption warrants systematic examination, and that behavioral science offers frameworks that bring clarity to …
• MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs
  We present MultiChallenge, a pioneering benchmark evaluating large language models (LLMs) on conducting multi-turn conversations with human users, a crucial yet underexamined capability for their appl…
• NoveltyBench: Evaluating Language Models for Humanlike Diversity
  Language models have demonstrated remarkable capabilities on standard benchmarks, yet they struggle increasingly from mode collapse, the inability to generate diverse and novel outputs. Our work intro…
• Off-Policy Evaluation for Large Action Spaces via Policy Convolution
  For example, consider a scenario where the logging policy in a movie recommendation platform, for a given segment of users, rarely recommends romantic movies. This can often happen when we think a use…
• On the Reasoning Capacity of AI Models and How to Quantify It
  Through controlled experiments on reasoning benchmarks, we show that true reasoning remains challenging for current models, with apparent success often relying on sophisticated combinations of memoriz…
• OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
  Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder reasoning problems. …
• Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution
  Large Language Models (LLMs) are widely used as automated judges, where practical value depends on both accuracy and trustworthy, risk-aware judgments. Existing approaches predominantly focus on accur…
• PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts
  We introduce PRELUDE, a benchmark for evaluating long-context understanding through the task of determining whether a character’s prequel story is consistent with the canonical narrative of the origin…
• Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  Large language models interact with users through a simulated “Assistant” persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviates from these ideals…
• Perturbation CheckLists for Evaluating NLG Evaluation Metrics
  We see that, across tasks, for most pairs of criteria, the correlation is moderate (between 0.3 and 0.5) to low (< 0:3). The highest correlation of 0.76 is observed between interestingness and enjoyab…
• Position: Towards Bidirectional Human-AI Alignment
  chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://arxiv.org/pdf/2406.09264 [[Human Centered Design]] [[Evaluations]] Recent advances in general-purpose AI underscore the urgent need to ali…
• ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
  Our extensive study, spanning multiple tasks, uncovers that prompt sensitivity fluctuates across datasets and models, with larger models exhibiting enhanced robustness. We observe that few-shot exampl…
• Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem
  The car wash problem asks a simple question: “I want to wash my car. The car wash is 100 meters away. Should I walk or drive?” Every major LLM tested—Claude, GPT-4, Gemini— recommended walking. The co…
• Quantifying Human-AI Synergy
  We introduce a novel Bayesian Item Response Theory framework to quantify human– AI synergy, separating individual and collaborative ability while controlling for task difficulty in interactive setting…
• ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question Answering
  In this paper, we propose a new dataset, ReasonVQA, for the Visual Question Answering (VQA) task. Our dataset is automatically integrated with structured encyclopedic knowledge and constructed using a…
• Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration
  theoretical analysis, we provide the first explanation of the RAG ensemble framework from the perspective of information entropy. In terms of mechanism analysis, we have explored the RAG ensemble fram…
• RewardBench: Evaluating Reward Models for Language Modeling
  To enhance scientific understanding of reward models, we present REWARDBENCH, a benchmark dataset and code-base for evaluation. The REWARDBENCH dataset is a collection of prompt-chosen-rejected trios …
• S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning Models
  We introduce S1-Bench, a novel benchmark designed to evaluate Large Reasoning Models’ (LRMs) performance on simple tasks that favor intuitive system 1 thinking rather than deliberative system 2 reason…
• Self-critiquing models for assisting human evaluators
  We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our mode…
• Stress Testing Deliberative Alignment for Anti-Scheming Training
  Highly capable AI systems could secretly pursue misaligned goals – what we call “scheming”. Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigat…
• Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
  We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a “teacher” model with some trait T (su…
• Survey on Evaluation of LLM-based Agents
  This paper provides the first comprehensive survey of evaluation methodologies for these increasingly capable agents. We systematically analyze evaluation benchmarks and frameworks across four critica…
• TaskLAMA: Probing the Complex Task Understanding of Language Models
  “Structured Complex Task Decomposition (SCTD) is the problem of breaking down a complex real-world task (such as planning a wedding) into a directed acyclic graph over individual steps that contribute…
• The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs
  Large language models (LLMs) have revolutionized natural language processing, yet their tendency to hallucinate poses serious challenges for reliable deployment. Despite numerous hallucination detecti…
• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
  Current evaluations primarily focus on established mathematical and coding benchmarks, emphasizing final answer accuracy. However, this evaluation paradigm often suffers from data contamination and do…
• The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
  Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint. We study this through a diagnose–measure–bridge–treat framework. Causal-behavior…
• TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
  To measure the progress of these LLM agents’ performance on performing real-world professional tasks, in this paper we introduce TheAgentCompany, an extensible benchmark for evaluating AI agents that …
• Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models
  In this position paper, we seek to answer two road-blocking questions: (1) How can we taxonomize a holistic landscape of machine ToM? (2) What is a more effective evaluation protocol for machine ToM? …
• Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?
  With the growing popularity of deep-learning based NLP models, comes a need for interpretable systems. But what is interpretability, and what constitutes a high-quality interpretation? In this opinion…
• Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
  we observe two qualitative phenomena in SAE training: feature occlusion (where a causally relevant concept is robustly overshadowed by even slightly higher-magnitude ones in the learned features), and…
• Towards a Science of Scaling Agent Systems
  Agents, language model (LM)-based systems that are capable of reasoning, planning, and acting are becoming the dominant paradigm for real-world AI applications. Despite this widespread adoption, the p…
• User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal
  Once language models (LMs) are deployed, they can interact with users long-term, ideally evolving continuously based on their feedback. Asking for direct user feedback can be disruptive; thus, we stud…
• When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs
  As large language models (LLMs) grow in capability and autonomy, evaluating their outputs— especially in open-ended and complex tasks—has become a critical bottleneck. A new paradigm is emerging: usin…
• When More is Less: Understanding Chain-of-Thought Length in LLMs
  Large Language Models (LLMs) employ Chain-of-Thought (CoT) reasoning to deconstruct complex problems. While longer CoTs are often presumed superior, this paper challenges that notion, arguing that lon…
• When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection
  The landscape of scientific peer review is rapidly evolving with the integration of Large Language Models (LLMs). This shift is driven by two parallel trends: the widespread individual adoption of LLM…
• Why Do Multi-agent LLM Systems Fail?
  [[Routers]] Despite growing enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains across popular benchmarks often remain minimal compared to single-agent frameworks. This gap highlig…
• Why Do Some Language Models Fake Alignment While Others Don't?
  Results from perturbing details of the scenario suggest that only Claude 3 Opus’s compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many ch…