Abstract Counterfactuals for Language Model Agents

• URL: http://arxiv.org/abs/2506.02946v1
• Date: Tue, 03 Jun 2025 14:44:26 GMT
• Title: Abstract Counterfactuals for Language Model Agents
• Abstract summary: Abstract Counterfactuals is a framework that emphasises high-level characteristics of actions and interactions within an environment.<n>We conduct experiments on text-based games and counterfactual text generation, while considering both token-level and latent-space interventions.
• Score: 3.7540612510652176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Counterfactual inference is a powerful tool for analysing and evaluating autonomous agents, but its application to language model (LM) agents remains challenging. Existing work on counterfactuals in LMs has primarily focused on token-level counterfactuals, which are often inadequate for LM agents due to their open-ended action spaces. Unlike traditional agents with fixed, clearly defined action spaces, the actions of LM agents are often implicit in the strings they output, making their action spaces difficult to define and interpret. Furthermore, the meanings of individual tokens can shift depending on the context, adding complexity to token-level reasoning and sometimes leading to biased or meaningless counterfactuals. We introduce \emph{Abstract Counterfactuals}, a framework that emphasises high-level characteristics of actions and interactions within an environment, enabling counterfactual reasoning tailored to user-relevant features. Our experiments demonstrate that the approach produces consistent and meaningful counterfactuals while minimising the undesired side effects of token-level methods. We conduct experiments on text-based games and counterfactual text generation, while considering both token-level and latent-space interventions.

Related papers

• Towards Explainability of SLMs by investigating Token Level Activation [2.7590644934977764]
  This work introduces a framework for quantifying token-level representational importance using hidden-state activation strengths at Layer 8 of BERT.<n>The proposed Activation Flow Network (AFN) framework computes Token Activation Strength using the L2 norm of Layer-8 hidden representations.<n>The study further introduces a threshold-based activation bucket formulation that partitions tokens into HIGH-activation and LOW-activation groups.
  arXiv  Detail & Related papers  (2026-05-21T12:09:12Z)
• ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both [55.182037225013836]
  ATLAS is a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation and a latent visual reasoning unit.<n> ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability.
  arXiv  Detail & Related papers  (2026-05-14T17:59:55Z)
• Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs [100.02824137397464]
  We investigate how Large Language Models adapt their internal representations when encountering inputs of increasing difficulty.<n>We reveal a consistent and quantifiable phenomenon: as task difficulty increases, the last hidden states of LLMs become substantially sparser.<n>This sparsity--difficulty relation is observable across diverse models and domains.
  arXiv  Detail & Related papers  (2026-03-03T18:48:15Z)
• Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction [2.5450067638785945]
  This study introduces Conditioned Comment Prediction (CCP), a task in which a model predicts how a user would comment on a given stimulus.<n>We evaluate open-weight 8B models (Llama3.1, Qwen3, Ministral) in English, German, and Luxembourgish language scenarios.
  arXiv  Detail & Related papers  (2026-02-26T08:40:21Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Behavior Tokens Speak Louder: Disentangled Explainable Recommendation with Behavior Vocabulary [22.925582428795437]
  BEAT is a framework that tokenizes user and item behaviors into discrete, interpretable sequences.<n>We show that BEAT improves zero-shot recommendation performance while generating coherent and informative explanations.
  arXiv  Detail & Related papers  (2025-12-17T17:24:24Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• A Controllable Examination for Long-Context Language Models [62.845852724511964]
  This study introduces $textbfLongBioBench, a benchmark for evaluating long-context language models.<n>We show that most models still exhibit deficiencies in semantic understanding and elementary reasoning over retrieved results.<n>Our further analysis indicates some design choices employed by existing synthetic benchmarks, such as contextual non-coherence.
  arXiv  Detail & Related papers  (2025-06-03T14:23:06Z)
• Computation Mechanism Behind LLM Position Generalization [59.013857707250814]
  Large language models (LLMs) exhibit flexibility in handling textual positions.<n>They can understand texts with position perturbations and generalize to longer texts.<n>This work connects the linguistic phenomenon with LLMs' computational mechanisms.
  arXiv  Detail & Related papers  (2025-03-17T15:47:37Z)
• AgentOrca: A Dual-System Framework to Evaluate Language Agents on Operational Routine and Constraint Adherence [54.317522790545304]
  We present AgentOrca, a dual-system framework for evaluating language agents' compliance with operational constraints and routines.<n>Our framework encodes action constraints and routines through both natural language prompts for agents and corresponding executable code serving as ground truth for automated verification.<n>Our findings reveal notable performance gaps among state-of-the-art models, with large reasoning models like o1 demonstrating superior compliance while others show significantly lower performance.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment [18.256529559741075]
  Large Language Models (LLMs) serve as key components in agent systems, where their common-sense knowledge significantly impacts performance as language-based planners for situated or embodied action.<n>We assess LLMs' incremental learning (based on feedback from the environment), and controlled in-context learning abilities using a text-based environment.<n>Results show that larger commercial models have a substantial gap in performance compared to open-weight but almost all models struggle with the synthetic words experiments.
  arXiv  Detail & Related papers  (2025-02-17T12:20:39Z)
• PromptExp: Multi-granularity Prompt Explanation of Large Language Models [16.259208045898415]
  We introduce PromptExp, a framework for multi-granularity prompt explanations by aggregating token-level insights. PromptExp supports both white-box and black-box explanations and extends explanations to higher granularity levels. We evaluate PromptExp in case studies such as sentiment analysis, showing the perturbation-based approach performs best.
  arXiv  Detail & Related papers  (2024-10-16T22:25:15Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data [3.376269351435396]
  We develop a formal perspective on probing using structural causal models (SCM) We extend a recent study of LMs in the context of a synthetic grid-world navigation task. Our techniques provide robust empirical evidence for the ability of LMs to induce the latent concepts underlying text.
  arXiv  Detail & Related papers  (2024-07-18T17:59:27Z)
• Unveiling and Manipulating Prompt Influence in Large Language Models [12.04811490937078]
  Token Distribution Dynamics (TDD) is a textcolorblacksimple yet effective approach to unveil and manipulate the role of prompts in generating Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2024-05-20T09:15:36Z)
• Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis [22.755345889167934]
  We present an interactive visualization system that enables exploration of large language models (LLMs) through counterfactual analysis.<n>Our system features a novel algorithm that generates fluent and semantically meaningful counterfactuals.<n>A user study with LLM practitioners and interviews with experts demonstrate the system's usability and effectiveness.
  arXiv  Detail & Related papers  (2024-04-23T19:57:03Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents [80.5213198675411]
  Large language models (LLMs) have dramatically enhanced the field of language intelligence. LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. Recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents.
  arXiv  Detail & Related papers  (2023-11-20T14:30:55Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)
• Augmented Language Models: a Survey [55.965967655575454]
  This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. We refer to them as Augmented Language Models (ALMs) The missing token objective allows ALMs to learn to reason, use tools, and even act, while still performing standard natural language tasks.
  arXiv  Detail & Related papers  (2023-02-15T18:25:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.