pith. sign in

arxiv: 2103.14659 · v1 · pith:H2A2V5QWnew · submitted 2021-03-26 · 💻 cs.AI · cs.LG

Alignment of Language Agents

classification 💻 cs.AI cs.LG
keywords someagentsissueslanguagemisspecificationbehaviouraldiscusshumans
0
0 comments X
read the original abstract

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by the system designer. We highlight some ways that misspecification can occur and discuss some behavioural issues that could arise from misspecification, including deceptive or manipulative language, and review some approaches for avoiding these issues.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Discovering Latent Knowledge in Language Models Without Supervision

    cs.CL 2022-12 conditional novelty 8.0

    An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average acros...

  2. A Generalist Agent

    cs.AI 2022-05 accept novelty 7.0

    Gato is a multi-modal, multi-task, multi-embodiment generalist policy using one transformer network to handle text, vision, games, and robotics tasks.

  3. OPT: Open Pre-trained Transformer Language Models

    cs.CL 2022-05 unverdicted novelty 7.0

    OPT releases open decoder-only transformers up to 175B parameters that match GPT-3 performance at one-seventh the carbon cost, along with code and training logs.

  4. Deep Pre-Alignment for VLMs

    cs.CV 2026-05 unverdicted novelty 6.0

    Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.

  5. WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation

    cs.CL 2026-05 unverdicted novelty 6.0

    WeatherSyn is the first instruction-tuned MLLM for weather forecasting report generation, outperforming closed-source models on a new dataset of 31 US cities across 8 weather aspects.

  6. Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights

    cs.CY 2025-02 unverdicted novelty 6.0

    LLMs exhibit identity-dependent hedging on human rights questions, with group identity as the strongest predictor among tested factors, and group steering mitigates the disparity.

  7. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

    cs.AI 2023-03 conditional novelty 6.0

    CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.

  8. Solving math word problems with process- and outcome-based feedback

    cs.LG 2022-11 unverdicted novelty 6.0

    On GSM8K, outcome-based supervision achieves similar final-answer error rates to process-based with less labeling, but process-based or learned reward models are needed to reach 3.4% reasoning error among correct solutions.

  9. LaMDA: Language Models for Dialog Applications

    cs.CL 2022-01 unverdicted novelty 6.0

    LaMDA shows that fine-tuning on human-value annotations and consulting external knowledge sources significantly improves safety and factual grounding in large dialog models beyond what scaling alone achieves.

  10. Ethical and social risks of harm from Language Models

    cs.CL 2021-12 accept novelty 6.0

    The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job...

  11. Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

    cs.AI 2023-08 accept novelty 5.0

    Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.

  12. AI Alignment From Social Choice Perspectives

    cs.AI 2026-06 unverdicted novelty 3.0

    This survey examines applications of social choice theory to aggregating human feedback in AI alignment, identifying failure modes and expanding design options for disagreement.